--- # Source: k8s-nim-operator/crds/apps.nvidia.com_nemocustomizers.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.0 name: nemocustomizers.apps.nvidia.com spec: group: apps.nvidia.com names: kind: NemoCustomizer listKind: NemoCustomizerList plural: nemocustomizers singular: nemocustomizer scope: Namespaced versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - format: date-time jsonPath: .metadata.creationTimestamp name: Age type: date name: v1alpha1 schema: openAPIV3Schema: description: NemoCustomizer is the Schema for the NemoCustomizer API. properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string metadata: type: object spec: description: NemoCustomizerSpec defines the desired state of NemoCustomizer. properties: affinity: description: Affinity is a group of affinity scheduling rules. properties: nodeAffinity: description: Describes node affinity scheduling rules for the pod. properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. items: description: |- An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). properties: preference: description: A node selector term, associated with the corresponding weight. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic weight: description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. format: int32 type: integer required: - preference - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. properties: nodeSelectorTerms: description: Required. A list of node selector terms. The terms are ORed. items: description: |- A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic type: array x-kubernetes-list-type: atomic required: - nodeSelectorTerms type: object x-kubernetes-map-type: atomic type: object podAffinity: description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object podAntiAffinity: description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and subtracting "weight" from the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object type: object annotations: additionalProperties: type: string type: object args: items: type: string type: array command: items: type: string type: array databaseConfig: description: DatabaseConfig stores the database configuration properties: credentials: description: |- DatabaseCredentials stores the configuration to retrieve the database credentials. Required, must not be nil. properties: passwordKey: default: password description: |- PasswordKey is the name of the key in the `CredentialsSecret` secret for the database credentials. Defaults to "password". type: string secretName: description: |- SecretName is the name of the secret which has the database credentials for a NEMO service user. Required, must not be empty. minLength: 1 type: string user: description: |- User is the non-root username for a NEMO Service in the database. Required, must not be empty. minLength: 1 type: string required: - secretName - user type: object databaseName: description: |- DatabaseName is the database name for a NEMO Service. Required, must not be empty. minLength: 1 type: string host: description: |- Host is the hostname of the database. Required, must not be empty. minLength: 1 type: string port: default: 5432 description: |- Port is the port where the database is reachable at. If specified, this must be a valid port number, 0 < databasePort < 65536. Defaults to 5432. format: int32 maximum: 65535 minimum: 1 type: integer required: - credentials - databaseName - host type: object datastore: description: Datastore stores the datastore endpoint. properties: endpoint: minLength: 1 pattern: ^http type: string required: - endpoint type: object entitystore: description: Entitystore stores the entitystore endpoint. properties: endpoint: minLength: 1 pattern: ^http type: string required: - endpoint type: object env: items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array expose: description: DEPRECATED ExposeV1 defines attributes to expose the service. properties: ingress: description: |- Deprecated: Use .spec.expose.router.ingress instead. IngressV1 defines attributes for ingress properties: annotations: additionalProperties: type: string type: object enabled: type: boolean spec: properties: host: type: string ingressClassName: pattern: '[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*' type: string paths: items: description: IngressPath defines attributes for ingress paths. properties: path: default: / type: string pathType: default: Prefix description: PathType represents the type of path referred to by a HTTPIngressPath. type: string type: object type: array required: - ingressClassName type: object type: object x-kubernetes-validations: - message: spec cannot be nil when ingress is enabled rule: (has(self.spec) && has(self.enabled) && self.enabled) || !has(self.enabled) || !self.enabled router: properties: annotations: additionalProperties: type: string description: Annotations for the router, e.g. for ingress class or gateway type: object eppConfig: description: EPPConfig is the configuration for the endpoint picker extension. This is field is currently only supported for standalone inference platform only on NIMService. properties: config: description: |- Config allows specifying EPP EndpointPickerConfig directly as a structured object. The operator will marshal this to YAML and create a ConfigMap automatically. Mutually exclusive with ConfigMapRef. One of ConfigMapRef or Config must be specified (no default configuration). Uses the upstream type from github.com/kubernetes-sigs/gateway-api-inference-extension properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string data: description: Data configures the DataLayer. It is required if the new DataLayer is enabled. properties: sources: description: Sources is the list of sources to define to the DataLayer items: description: DataLayerSource contains the configuration of a DataSource of the DataLayer feature properties: extractors: description: |- Extractors specifies the list of Plugin instances to be associated with this Source. The entries are references to the names of entries of the Plugins defined in the configuration's Plugins section items: description: DataLayerExtractor contains the configuration of an Extractor of the DataLayer feature properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Extractor. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - pluginRef type: object type: array pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Source. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - extractors - pluginRef type: object type: array required: - sources type: object featureGates: description: |- FeatureGates is a set of flags that enable various experimental features with the EPP. If omitted non of these experimental features will be enabled. items: type: string type: array kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string plugins: description: Plugins is the list of plugins that will be instantiated. items: description: |- PluginSpec contains the information that describes a plugin that will be instantiated. properties: name: description: |- Name provides a name for plugin entries to reference. If omitted, the value of the Plugin's Type field will be used. type: string parameters: description: |- Parameters are the set of parameters to be passed to the plugin's factory function. The factory function is responsible to parse the parameters. format: byte type: string type: description: Type specifies the plugin type to be instantiated. type: string required: - type type: object type: array saturationDetector: description: |- SaturationDetector when present specifies the configuration of the Saturation detector. If not present, default values are used. properties: kvCacheUtilThreshold: description: |- KVCacheUtilThreshold defines the KV cache utilization (0.0 to 1.0) above which a pod is considered to have insufficient capacity. type: number metricsStalenessThreshold: description: |- MetricsStalenessThreshold defines how old a pod's metrics can be. If a pod's metrics are older than this, it might be excluded from "good capacity" considerations or treated as having no capacity for safety. type: string queueDepthThreshold: description: |- QueueDepthThreshold defines the backend waiting queue size above which a pod is considered to have insufficient capacity for new requests. type: integer type: object schedulingProfiles: description: |- SchedulingProfiles is the list of named SchedulingProfiles that will be created. items: description: |- SchedulingProfile contains the information to create a SchedulingProfile entry to be used by the scheduler. properties: name: description: Name specifies the name of this SchedulingProfile type: string plugins: description: |- Plugins is the list of plugins for this SchedulingProfile. They are assigned to the appropriate "slots" based on their type. items: description: |- SchedulingPlugin describes a plugin that will be associated with a SchedulingProfile entry. properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this SchedulingProfile. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string weight: description: Weight is the weight fo be used if this plugin is a Scorer. type: integer required: - pluginRef type: object type: array required: - name - plugins type: object type: array required: - plugins - schedulingProfiles type: object x-kubernetes-preserve-unknown-fields: true configMapRef: description: |- ConfigMapRef references a user-provided ConfigMap containing EPP configuration. The ConfigMap should contain EndpointPickerConfig YAML. Mutually exclusive with Config. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic containerSpec: description: ContainerSpec is the specification for the EPP container. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object livenessProbe: description: LivenessProbe is the liveness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object ports: description: Ports is the list of ports to expose for the EPP container. items: description: ContainerPort represents a network port in a single container. properties: containerPort: description: |- Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. format: int32 type: integer hostIP: description: What host IP to bind the external port to. type: string hostPort: description: |- Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. format: int32 type: integer name: description: |- If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. type: string protocol: default: TCP description: |- Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". type: string required: - containerPort type: object type: array readinessProbe: description: ReadinessProbe is the readiness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object startupProbe: description: StartupProbe is the startup probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object required: - containerSpec type: object x-kubernetes-validations: - message: specify either configMapRef or config, not both rule: '!(has(self.configMapRef) && has(self.config))' gateway: description: Gateway is the gateway to use for the created HTTPRoute. properties: backendRef: description: BackendRef is a reference to a backend to forward matched requests to. properties: group: default: "" description: |- Group is the group of the referent. For example, "gateway.networking.k8s.io". When unspecified or empty string, core API group is inferred. maxLength: 253 pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ type: string kind: default: Service description: |- Kind is the Kubernetes resource kind of the referent. For example "Service". Defaults to "Service" when not specified. ExternalName services can refer to CNAME DNS records that may live outside of the cluster and as such are difficult to reason about in terms of conformance. They also may not be safe to forward to (see CVE-2021-25740 for more information). Implementations SHOULD NOT support ExternalName Services. Support: Core (Services with a type other than ExternalName) Support: Implementation-specific (Services with type ExternalName) maxLength: 63 minLength: 1 pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$ type: string name: description: Name is the name of the referent. maxLength: 253 minLength: 1 type: string namespace: description: |- Namespace is the namespace of the backend. When unspecified, the local namespace is inferred. Note that when a namespace different than the local namespace is specified, a ReferenceGrant object is required in the referent namespace to allow that namespace's owner to accept the reference. See the ReferenceGrant documentation for details. Support: Core maxLength: 63 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ type: string port: description: |- Port specifies the destination port number to use for this resource. Port is required when the referent is a Kubernetes Service. In this case, the port number is the service port number, not the target port. For other resources, destination port might be derived from the referent resource or this field. format: int32 maximum: 65535 minimum: 1 type: integer weight: default: 1 description: |- Weight specifies the proportion of requests forwarded to the referenced backend. This is computed as weight/(sum of all weights in this BackendRefs list). For non-zero values, there may be some epsilon from the exact proportion defined here depending on the precision an implementation supports. Weight is not a percentage and the sum of weights does not need to equal 100. If only one backend is specified and it has a weight greater than 0, 100% of the traffic is forwarded to that backend. If weight is set to 0, no traffic should be forwarded for this entry. If unspecified, weight defaults to 1. Support for this field varies based on the context where used. format: int32 maximum: 1000000 minimum: 0 type: integer required: - name type: object x-kubernetes-validations: - message: Must have port for Service reference rule: '(size(self.group) == 0 && self.kind == ''Service'') ? has(self.port) : true' grpcRoutesEnabled: default: false description: GRPCRoutesEnabled is a flag to enable GRPCRoutes for the created gateway. type: boolean httpRoutesEnabled: default: true description: HTTPRoutesEnabled is a flag to enable HTTPRoutes for the created gateway. type: boolean name: description: Name of the gateway minLength: 1 type: string namespace: description: Namespace of the gateway minLength: 1 type: string required: - name - namespace type: object hostDomainName: description: |- HostDomainName is the domain name of the hostname matched by the router. The hostname is constructed as "..", where the a subdomain of the matched hostname. eg. example.com for "..example.com" maxLength: 63 minLength: 1 pattern: ^(([a-z0-9][a-z0-9\-]*[a-z0-9])|[a-z0-9]+\.)*([a-z]+|xn\-\-[a-z0-9]+)\.?$ type: string ingress: description: Ingress is the ingress controller to use for the created ingress. properties: ingressClass: description: IngressClass is the ingress class to use for the created ingress. minLength: 1 type: string tlsSecretName: description: TLSSecretName is the name of the secret containing the TLS certificate and key. type: string required: - ingressClass type: object type: object x-kubernetes-validations: - message: 'unsupported field: spec.expose.router.gateway.grpcRoutesEnabled' rule: '!(has(self.gateway) && self.gateway.grpcRoutesEnabled)' - message: ingress and gateway cannot be specified together rule: '!(has(self.gateway) && has(self.ingress))' service: description: Service defines attributes to create a service. properties: annotations: additionalProperties: type: string type: object grpcPort: description: |- GRPCPort is the GRPC serving port Note: This port is only applicable for NIMs that runs a Triton GRPC Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer metricsPort: description: |- MetricsPort is the port for metrics Note: This port is only applicable for NIMs that runs a separate metrics endpoint on Triton Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer name: description: Override the default service name type: string port: default: 8000 description: 'Port is the main api serving port (default: 8000)' format: int32 maximum: 65535 minimum: 1 type: integer type: description: Service Type string describes ingress methods for a service type: string type: object type: object x-kubernetes-validations: - message: 'unsupported field: spec.expose.service.grpcPort' rule: '!(has(self.service.grpcPort))' - message: 'unsupported field: spec.expose.service.metricsPort' rule: '!(has(self.service.metricsPort))' groupID: format: int64 type: integer image: description: Image defines image attributes. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object labels: additionalProperties: type: string type: object metrics: description: Metrics defines attributes to setup metrics collection. properties: enabled: type: boolean serviceMonitor: description: for use with the Prometheus Operator and the primary service object properties: additionalLabels: additionalProperties: type: string type: object annotations: additionalProperties: type: string type: object interval: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string scrapeTimeout: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string type: object type: object mlflow: description: MLFlow stores the mlflow tracking endpoint. properties: endpoint: minLength: 1 pattern: ^http type: string required: - endpoint type: object modelConfig: description: Models stores the model configuration properties: name: minLength: 1 type: string required: - name type: object modelDownloadJobs: description: Model download job configuration properties: hfSecret: description: HFSecret is the secret containing the HF_TOKEN key properties: key: default: HF_TOKEN description: Key in the key containing the actual token value type: string name: description: Name of the Kubernetes secret containing HF_TOKEN key minLength: 1 type: string required: - key - name type: object image: description: Docker image used for model download jobs minLength: 1 type: string imagePullPolicy: default: IfNotPresent description: Pull policy for the image enum: - Always - IfNotPresent - Never type: string ngcAPISecret: description: NGCSecret is the secret containing the NGC API key properties: key: default: NGC_API_KEY description: Key in the key containing the actual API key value type: string name: description: Name of the Kubernetes secret containing NGC API key minLength: 1 type: string required: - key - name type: object pollIntervalSeconds: description: Polling interval for model download status minimum: 15 type: integer securityContext: description: Optional security context for the job pods properties: appArmorProfile: description: |- appArmorProfile is the AppArmor options to use by the containers in this pod. Note that this field cannot be set when spec.os.name is windows. properties: localhostProfile: description: |- localhostProfile indicates a profile loaded on the node that should be used. The profile must be preconfigured on the node to work. Must match the loaded name of the profile. Must be set if and only if type is "Localhost". type: string type: description: |- type indicates which kind of AppArmor profile will be applied. Valid options are: Localhost - a profile pre-loaded on the node. RuntimeDefault - the container runtime's default profile. Unconfined - no AppArmor enforcement. type: string required: - type type: object fsGroup: description: |- A special supplemental group that applies to all containers in a pod. Some volume types allow the Kubelet to change the ownership of that volume to be owned by the pod: 1. The owning GID will be the FSGroup 2. The setgid bit is set (new files created in the volume will be owned by FSGroup) 3. The permission bits are OR'd with rw-rw---- If unset, the Kubelet will not modify the ownership and permissions of any volume. Note that this field cannot be set when spec.os.name is windows. format: int64 type: integer fsGroupChangePolicy: description: |- fsGroupChangePolicy defines behavior of changing ownership and permission of the volume before being exposed inside Pod. This field will only apply to volume types which support fsGroup based ownership(and permissions). It will have no effect on ephemeral volume types such as: secret, configmaps and emptydir. Valid values are "OnRootMismatch" and "Always". If not specified, "Always" is used. Note that this field cannot be set when spec.os.name is windows. type: string runAsGroup: description: |- The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. format: int64 type: integer runAsNonRoot: description: |- Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. type: boolean runAsUser: description: |- The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. format: int64 type: integer seLinuxChangePolicy: description: |- seLinuxChangePolicy defines how the container's SELinux label is applied to all volumes used by the Pod. It has no effect on nodes that do not support SELinux or to volumes does not support SELinux. Valid values are "MountOption" and "Recursive". "Recursive" means relabeling of all files on all Pod volumes by the container runtime. This may be slow for large volumes, but allows mixing privileged and unprivileged Pods sharing the same volume on the same node. "MountOption" mounts all eligible Pod volumes with `-o context` mount option. This requires all Pods that share the same volume to use the same SELinux label. It is not possible to share the same volume among privileged and unprivileged Pods. Eligible volumes are in-tree FibreChannel and iSCSI volumes, and all CSI volumes whose CSI driver announces SELinux support by setting spec.seLinuxMount: true in their CSIDriver instance. Other volumes are always re-labelled recursively. "MountOption" value is allowed only when SELinuxMount feature gate is enabled. If not specified and SELinuxMount feature gate is enabled, "MountOption" is used. If not specified and SELinuxMount feature gate is disabled, "MountOption" is used for ReadWriteOncePod volumes and "Recursive" for all other volumes. This field affects only Pods that have SELinux label set, either in PodSecurityContext or in SecurityContext of all containers. All Pods that use the same volume should use the same seLinuxChangePolicy, otherwise some pods can get stuck in ContainerCreating state. Note that this field cannot be set when spec.os.name is windows. type: string seLinuxOptions: description: |- The SELinux context to be applied to all containers. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. properties: level: description: Level is SELinux level label that applies to the container. type: string role: description: Role is a SELinux role label that applies to the container. type: string type: description: Type is a SELinux type label that applies to the container. type: string user: description: User is a SELinux user label that applies to the container. type: string type: object seccompProfile: description: |- The seccomp options to use by the containers in this pod. Note that this field cannot be set when spec.os.name is windows. properties: localhostProfile: description: |- localhostProfile indicates a profile defined in a file on the node should be used. The profile must be preconfigured on the node to work. Must be a descending path, relative to the kubelet's configured seccomp profile location. Must be set if type is "Localhost". Must NOT be set for any other type. type: string type: description: |- type indicates which kind of seccomp profile will be applied. Valid options are: Localhost - a profile defined in a file on the node should be used. RuntimeDefault - the container runtime default profile should be used. Unconfined - no profile should be applied. type: string required: - type type: object supplementalGroups: description: |- A list of groups applied to the first process run in each container, in addition to the container's primary GID and fsGroup (if specified). If the SupplementalGroupsPolicy feature is enabled, the supplementalGroupsPolicy field determines whether these are in addition to or instead of any group memberships defined in the container image. If unspecified, no additional groups are added, though group memberships defined in the container image may still be used, depending on the supplementalGroupsPolicy field. Note that this field cannot be set when spec.os.name is windows. items: format: int64 type: integer type: array x-kubernetes-list-type: atomic supplementalGroupsPolicy: description: |- Defines how supplemental groups of the first container processes are calculated. Valid values are "Merge" and "Strict". If not specified, "Merge" is used. (Alpha) Using the field requires the SupplementalGroupsPolicy feature gate to be enabled and the container runtime must implement support for this feature. Note that this field cannot be set when spec.os.name is windows. type: string sysctls: description: |- Sysctls hold a list of namespaced sysctls used for the pod. Pods with unsupported sysctls (by the container runtime) might fail to launch. Note that this field cannot be set when spec.os.name is windows. items: description: Sysctl defines a kernel parameter to be set properties: name: description: Name of a property to set type: string value: description: Value of a property to set type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic windowsOptions: description: |- The Windows specific settings applied to all containers. If unspecified, the options within a container's SecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is linux. properties: gmsaCredentialSpec: description: |- GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. type: string gmsaCredentialSpecName: description: GMSACredentialSpecName is the name of the GMSA credential spec to use. type: string hostProcess: description: |- HostProcess determines if a container should be run as a 'Host Process' container. All of a Pod's containers must have the same effective HostProcess value (it is not allowed to have a mix of HostProcess containers and non-HostProcess containers). In addition, if HostProcess is true then HostNetwork must also be set to true. type: boolean runAsUserName: description: |- The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. type: string type: object type: object ttlSecondsAfterFinished: description: Time to live after job finishes (seconds) minimum: 60 type: integer required: - image - pollIntervalSeconds - ttlSecondsAfterFinished type: object nemoDatastoreTools: description: Configuration for data store tools image properties: image: description: Image to use for data store CLI tools minLength: 1 type: string required: - image type: object nodeSelector: additionalProperties: type: string type: object otel: description: OpenTelemetry Settings properties: disableLogging: description: DisableLogging indicates whether Python logging auto-instrumentation should be disabled. type: boolean enabled: description: Enabled indicates if opentelemetry collector and tracing are enabled type: boolean excludedUrls: default: - health description: ExcludedUrls defines URLs to be excluded from tracing. items: type: string type: array exporterConfig: description: ExporterConfig defines configuration for different OTel exporters properties: logsExporter: default: otlp description: 'LogsExporter sets the logs exporter: (otlp, console, none).' enum: - otlp - console - none type: string metricsExporter: default: otlp description: 'MetricsExporter sets the metrics exporter: (otlp, console, none).' enum: - otlp - console - none type: string tracesExporter: default: otlp description: 'TracesExporter sets the traces exporter: (otlp, console, none).' enum: - otlp - console - none type: string type: object exporterOtlpEndpoint: description: ExporterOtlpEndpoint is the OTLP collector endpoint. type: string logLevel: default: INFO description: LogLevel defines the log level (e.g., INFO, DEBUG). enum: - INFO - DEBUG type: string type: object podAffinity: description: 'Deprecated: Use Affinity instead.' properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object replicas: format: int32 minimum: 1 type: integer resources: description: ResourceRequirements describes the compute resource requirements. properties: claims: description: |- Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. This field depends on the DynamicResourceAllocation feature gate. This field is immutable. It can only be set for containers. items: description: ResourceClaim references one entry in PodSpec.ResourceClaims. properties: name: description: |- Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. type: string request: description: |- Request is the name chosen for a request in the referenced claim. If empty, everything from the claim is made available, otherwise only the result of this request. type: string required: - name type: object type: array x-kubernetes-list-map-keys: - name x-kubernetes-list-type: map limits: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object runtimeClass: type: string scale: description: Autoscaling defines attributes to automatically scale the service based on metrics. properties: annotations: additionalProperties: type: string type: object enabled: type: boolean hpa: description: HorizontalPodAutoscalerSpec defines the parameters required to setup HPA. properties: behavior: description: |- HorizontalPodAutoscalerBehavior configures the scaling behavior of the target in both Up and Down directions (scaleUp and scaleDown fields respectively). properties: scaleDown: description: |- scaleDown is scaling policy for scaling Down. If not set, the default value is to allow to scale down to minReplicas pods, with a 300 second stabilization window (i.e., the highest recommendation for the last 300sec is used). properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object scaleUp: description: |- scaleUp is scaling policy for scaling Up. If not set, the default value is the higher of: * increase no more than 4 pods per 60 seconds * double the number of pods per 60 seconds No stabilization is used. properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object type: object maxReplicas: format: int32 type: integer metrics: items: description: |- MetricSpec specifies how to scale based on a single metric (only `type` and one other matching field should be set at once). properties: containerResource: description: |- containerResource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing a single container in each pod of the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: container: description: container is the name of the container in the pods of the scaling target type: string name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - container - name - target type: object external: description: |- external refers to a global metric that is not associated with any Kubernetes object. It allows autoscaling based on information coming from components running outside of cluster (for example length of queue in cloud messaging service, or QPS from loadbalancer running outside of cluster). properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object object: description: |- object refers to a metric describing a single kubernetes object (for example, hits-per-second on an Ingress object). properties: describedObject: description: describedObject specifies the descriptions of a object,such as kind,name apiVersion properties: apiVersion: description: apiVersion is the API version of the referent type: string kind: description: 'kind is the kind of the referent; More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'name is the name of the referent; More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' type: string required: - kind - name type: object metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - describedObject - metric - target type: object pods: description: |- pods refers to a metric describing each pod in the current scale target (for example, transactions-processed-per-second). The values will be averaged together before being compared to the target value. properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object resource: description: |- resource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing each pod in the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - name - target type: object type: description: |- type is the type of metric source. It should be one of "ContainerResource", "External", "Object", "Pods" or "Resource", each mapping to a matching field in the object. type: string required: - type type: object type: array minReplicas: default: 1 format: int32 minimum: 1 type: integer required: - maxReplicas type: object type: object scheduler: description: Scheduler Configuration properties: type: default: volcano description: Type is the scheduler type (volcano, runai) enum: - volcano - runai type: string type: object tolerations: items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array trainingConfig: description: Training stores the training configuration properties: affinity: description: Affinity for the training jobs properties: nodeAffinity: description: Describes node affinity scheduling rules for the pod. properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. items: description: |- An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). properties: preference: description: A node selector term, associated with the corresponding weight. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic weight: description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. format: int32 type: integer required: - preference - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. properties: nodeSelectorTerms: description: Required. A list of node selector terms. The terms are ORed. items: description: |- A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic type: array x-kubernetes-list-type: atomic required: - nodeSelectorTerms type: object x-kubernetes-map-type: atomic type: object podAffinity: description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object podAntiAffinity: description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and subtracting "weight" from the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object type: object configMap: description: ConfigMap is the training configuration in the config map properties: name: minLength: 1 type: string required: - name type: object env: description: Env are the environment variables passed to the training jobs items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image is the NeMo customizer image used for training properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object modelPVC: description: ModelPVC is the persistent storage for models used for finetuning properties: annotations: additionalProperties: type: string description: Annotations for the PVC type: object create: description: |- Create specifies whether to create a new PersistentVolumeClaim (PVC). If set to false, an existing PVC must be referenced via the `Name` field. type: boolean name: description: Name of the PVC to use. Required if `Create` is false (i.e., using an existing PVC). type: string size: description: Size of the NIM cache in Gi, used during PVC creation type: string storageClass: description: |- StorageClass to be used for PVC creation. Leave it as empty if the PVC is already created or a default storage class is set in the cluster. type: string subPath: description: SubPath is the path inside the PVC that should be mounted type: string volumeAccessMode: description: VolumeAccessMode is the volume access mode of the PVC type: string type: object networkConfig: description: NetworkConfig is the network configuration for multi-node training items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array nodeSelector: additionalProperties: type: string description: NodeSelector labels for scheduling training jobs type: object podAffinity: description: |- Deprecated: Use Affinity instead. PodAffinity for the training jobs properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object resources: description: Resources for the training jobs properties: claims: description: |- Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. This field depends on the DynamicResourceAllocation feature gate. This field is immutable. It can only be set for containers. items: description: ResourceClaim references one entry in PodSpec.ResourceClaims. properties: name: description: |- Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. type: string request: description: |- Request is the name chosen for a request in the referenced claim. If empty, everything from the claim is made available, otherwise only the result of this request. type: string required: - name type: object type: array x-kubernetes-list-map-keys: - name x-kubernetes-list-type: map limits: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object runaiQueue: default: default description: |- RunAIQueue is the Run.AI's scheduler queue to be used for training jobs. Used only if the scheduler is set to runai. type: string sharedMemorySizeLimit: anyOf: - type: integer - type: string description: SharedMemorySizeLimit sets the max size of the shared memory volume (emptyDir) used by the training jobs for fast model runtime I/O. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true timeout: description: Timeout for the training job to complete type: integer tolerations: description: Tolerations for the training jobs items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array ttlSecondsAfterFinished: description: Time to live after the training job finishes (seconds) type: integer workspacePVC: description: WorkspacePVC is the PVC config for NemoTrainingJob, which automatically creates one for each job properties: mountPath: default: /pvc/workspace description: MountPath is the path where the workspace pvc is mounted within the training job type: string size: description: Size of the workspace storage in Gi, used during PVC creation type: string storageClass: description: |- StorageClass to be used for PVC creation. Leave it as empty if a default storage class is set in the cluster. type: string volumeAccessMode: description: VolumeAccessMode is the volume access mode of the PVC type: string type: object required: - image - modelPVC - workspacePVC type: object userID: format: int64 type: integer wandb: description: WandBConfig stores the config for the Weights and Biases service. properties: apiKeyKey: default: apiKey description: |- APIKeyKey is the key in the Secret that holds the WandB API key. Defaults to "apiKey". minLength: 1 type: string encryptionKey: default: encryptionKey description: |- EncryptionKey is an optional key in the secret used for encrypting WandB credentials. This can be used for additional security layers if required. Defaults to "encryptionKey". type: string entity: default: "null" description: |- Entity is the username or team name under which the runs will be logged. If not specified, the run will default to your default entity To change the default entity, go to the account settings https://wandb.ai/settings and update the “Default location to create new projects” under “Default team”. type: string projectName: default: nvidia-nemo-customizer description: Project is the name of the project under which this run will be logged type: string secretName: description: |- SecretName is the name of the Kubernetes Secret containing the WandB API key. Required, must not be empty. minLength: 1 type: string required: - apiKeyKey - secretName type: object required: - databaseConfig - datastore - entitystore - image - mlflow - modelConfig - modelDownloadJobs - nemoDatastoreTools - trainingConfig - wandb type: object x-kubernetes-validations: - message: .spec.expose.ingress is deprecated, and will be removed in a future release. If .spec.expose.ingress is set, please do not set .spec.expose.router.ingress. rule: '!(has(self.expose.ingress) && has(self.expose.ingress.enabled) && self.expose.ingress.enabled && has(self.expose.router) && has(self.expose.router.ingress))' - message: spec.replicas cannot be set when spec.scale.enabled is true rule: '!(has(self.scale) && has(self.scale.enabled) && self.scale.enabled && has(self.replicas))' status: description: NemoCustomizerStatus defines the observed state of NemoCustomizer. properties: availableReplicas: format: int32 type: integer conditions: items: description: Condition contains details for one aspect of the current state of this API Resource. properties: lastTransitionTime: description: |- lastTransitionTime is the last time the condition transitioned from one status to another. This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable. format: date-time type: string message: description: |- message is a human readable message indicating details about the transition. This may be an empty string. maxLength: 32768 type: string observedGeneration: description: |- observedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date with respect to the current state of the instance. format: int64 minimum: 0 type: integer reason: description: |- reason contains a programmatic identifier indicating the reason for the condition's last transition. Producers of specific condition types may define expected values and meanings for this field, and whether the values are considered a guaranteed API. The value should be a CamelCase string. This field may not be empty. maxLength: 1024 minLength: 1 pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$ type: string status: description: status of the condition, one of True, False, Unknown. enum: - "True" - "False" - Unknown type: string type: description: type of condition in CamelCase or in foo.example.com/CamelCase. maxLength: 316 pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$ type: string required: - lastTransitionTime - message - reason - status - type type: object type: array state: type: string type: object type: object served: true storage: true subresources: status: {} --- # Source: k8s-nim-operator/crds/apps.nvidia.com_nemodatastores.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.0 name: nemodatastores.apps.nvidia.com spec: group: apps.nvidia.com names: kind: NemoDatastore listKind: NemoDatastoreList plural: nemodatastores singular: nemodatastore scope: Namespaced versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - format: date-time jsonPath: .metadata.creationTimestamp name: Age type: date name: v1alpha1 schema: openAPIV3Schema: description: NemoDatastore is the Schema for the NemoDatastore API. properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string metadata: type: object spec: description: NemoDatastoreSpec defines the desired state of NemoDatastore. properties: affinity: description: Affinity is a group of affinity scheduling rules. properties: nodeAffinity: description: Describes node affinity scheduling rules for the pod. properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. items: description: |- An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). properties: preference: description: A node selector term, associated with the corresponding weight. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic weight: description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. format: int32 type: integer required: - preference - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. properties: nodeSelectorTerms: description: Required. A list of node selector terms. The terms are ORed. items: description: |- A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic type: array x-kubernetes-list-type: atomic required: - nodeSelectorTerms type: object x-kubernetes-map-type: atomic type: object podAffinity: description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object podAntiAffinity: description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and subtracting "weight" from the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object type: object annotations: additionalProperties: type: string type: object args: items: type: string type: array command: items: type: string type: array databaseConfig: description: DatabaseConfig contains external PostgreSQL configuration properties: credentials: description: |- DatabaseCredentials stores the configuration to retrieve the database credentials. Required, must not be nil. properties: passwordKey: default: password description: |- PasswordKey is the name of the key in the `CredentialsSecret` secret for the database credentials. Defaults to "password". type: string secretName: description: |- SecretName is the name of the secret which has the database credentials for a NEMO service user. Required, must not be empty. minLength: 1 type: string user: description: |- User is the non-root username for a NEMO Service in the database. Required, must not be empty. minLength: 1 type: string required: - secretName - user type: object databaseName: description: |- DatabaseName is the database name for a NEMO Service. Required, must not be empty. minLength: 1 type: string host: description: |- Host is the hostname of the database. Required, must not be empty. minLength: 1 type: string port: default: 5432 description: |- Port is the port where the database is reachable at. If specified, this must be a valid port number, 0 < databasePort < 65536. Defaults to 5432. format: int32 maximum: 65535 minimum: 1 type: integer required: - credentials - databaseName - host type: object env: items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array expose: description: DEPRECATED ExposeV1 defines attributes to expose the service. properties: ingress: description: |- Deprecated: Use .spec.expose.router.ingress instead. IngressV1 defines attributes for ingress properties: annotations: additionalProperties: type: string type: object enabled: type: boolean spec: properties: host: type: string ingressClassName: pattern: '[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*' type: string paths: items: description: IngressPath defines attributes for ingress paths. properties: path: default: / type: string pathType: default: Prefix description: PathType represents the type of path referred to by a HTTPIngressPath. type: string type: object type: array required: - ingressClassName type: object type: object x-kubernetes-validations: - message: spec cannot be nil when ingress is enabled rule: (has(self.spec) && has(self.enabled) && self.enabled) || !has(self.enabled) || !self.enabled router: properties: annotations: additionalProperties: type: string description: Annotations for the router, e.g. for ingress class or gateway type: object eppConfig: description: EPPConfig is the configuration for the endpoint picker extension. This is field is currently only supported for standalone inference platform only on NIMService. properties: config: description: |- Config allows specifying EPP EndpointPickerConfig directly as a structured object. The operator will marshal this to YAML and create a ConfigMap automatically. Mutually exclusive with ConfigMapRef. One of ConfigMapRef or Config must be specified (no default configuration). Uses the upstream type from github.com/kubernetes-sigs/gateway-api-inference-extension properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string data: description: Data configures the DataLayer. It is required if the new DataLayer is enabled. properties: sources: description: Sources is the list of sources to define to the DataLayer items: description: DataLayerSource contains the configuration of a DataSource of the DataLayer feature properties: extractors: description: |- Extractors specifies the list of Plugin instances to be associated with this Source. The entries are references to the names of entries of the Plugins defined in the configuration's Plugins section items: description: DataLayerExtractor contains the configuration of an Extractor of the DataLayer feature properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Extractor. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - pluginRef type: object type: array pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Source. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - extractors - pluginRef type: object type: array required: - sources type: object featureGates: description: |- FeatureGates is a set of flags that enable various experimental features with the EPP. If omitted non of these experimental features will be enabled. items: type: string type: array kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string plugins: description: Plugins is the list of plugins that will be instantiated. items: description: |- PluginSpec contains the information that describes a plugin that will be instantiated. properties: name: description: |- Name provides a name for plugin entries to reference. If omitted, the value of the Plugin's Type field will be used. type: string parameters: description: |- Parameters are the set of parameters to be passed to the plugin's factory function. The factory function is responsible to parse the parameters. format: byte type: string type: description: Type specifies the plugin type to be instantiated. type: string required: - type type: object type: array saturationDetector: description: |- SaturationDetector when present specifies the configuration of the Saturation detector. If not present, default values are used. properties: kvCacheUtilThreshold: description: |- KVCacheUtilThreshold defines the KV cache utilization (0.0 to 1.0) above which a pod is considered to have insufficient capacity. type: number metricsStalenessThreshold: description: |- MetricsStalenessThreshold defines how old a pod's metrics can be. If a pod's metrics are older than this, it might be excluded from "good capacity" considerations or treated as having no capacity for safety. type: string queueDepthThreshold: description: |- QueueDepthThreshold defines the backend waiting queue size above which a pod is considered to have insufficient capacity for new requests. type: integer type: object schedulingProfiles: description: |- SchedulingProfiles is the list of named SchedulingProfiles that will be created. items: description: |- SchedulingProfile contains the information to create a SchedulingProfile entry to be used by the scheduler. properties: name: description: Name specifies the name of this SchedulingProfile type: string plugins: description: |- Plugins is the list of plugins for this SchedulingProfile. They are assigned to the appropriate "slots" based on their type. items: description: |- SchedulingPlugin describes a plugin that will be associated with a SchedulingProfile entry. properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this SchedulingProfile. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string weight: description: Weight is the weight fo be used if this plugin is a Scorer. type: integer required: - pluginRef type: object type: array required: - name - plugins type: object type: array required: - plugins - schedulingProfiles type: object x-kubernetes-preserve-unknown-fields: true configMapRef: description: |- ConfigMapRef references a user-provided ConfigMap containing EPP configuration. The ConfigMap should contain EndpointPickerConfig YAML. Mutually exclusive with Config. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic containerSpec: description: ContainerSpec is the specification for the EPP container. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object livenessProbe: description: LivenessProbe is the liveness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object ports: description: Ports is the list of ports to expose for the EPP container. items: description: ContainerPort represents a network port in a single container. properties: containerPort: description: |- Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. format: int32 type: integer hostIP: description: What host IP to bind the external port to. type: string hostPort: description: |- Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. format: int32 type: integer name: description: |- If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. type: string protocol: default: TCP description: |- Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". type: string required: - containerPort type: object type: array readinessProbe: description: ReadinessProbe is the readiness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object startupProbe: description: StartupProbe is the startup probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object required: - containerSpec type: object x-kubernetes-validations: - message: specify either configMapRef or config, not both rule: '!(has(self.configMapRef) && has(self.config))' gateway: description: Gateway is the gateway to use for the created HTTPRoute. properties: backendRef: description: BackendRef is a reference to a backend to forward matched requests to. properties: group: default: "" description: |- Group is the group of the referent. For example, "gateway.networking.k8s.io". When unspecified or empty string, core API group is inferred. maxLength: 253 pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ type: string kind: default: Service description: |- Kind is the Kubernetes resource kind of the referent. For example "Service". Defaults to "Service" when not specified. ExternalName services can refer to CNAME DNS records that may live outside of the cluster and as such are difficult to reason about in terms of conformance. They also may not be safe to forward to (see CVE-2021-25740 for more information). Implementations SHOULD NOT support ExternalName Services. Support: Core (Services with a type other than ExternalName) Support: Implementation-specific (Services with type ExternalName) maxLength: 63 minLength: 1 pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$ type: string name: description: Name is the name of the referent. maxLength: 253 minLength: 1 type: string namespace: description: |- Namespace is the namespace of the backend. When unspecified, the local namespace is inferred. Note that when a namespace different than the local namespace is specified, a ReferenceGrant object is required in the referent namespace to allow that namespace's owner to accept the reference. See the ReferenceGrant documentation for details. Support: Core maxLength: 63 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ type: string port: description: |- Port specifies the destination port number to use for this resource. Port is required when the referent is a Kubernetes Service. In this case, the port number is the service port number, not the target port. For other resources, destination port might be derived from the referent resource or this field. format: int32 maximum: 65535 minimum: 1 type: integer weight: default: 1 description: |- Weight specifies the proportion of requests forwarded to the referenced backend. This is computed as weight/(sum of all weights in this BackendRefs list). For non-zero values, there may be some epsilon from the exact proportion defined here depending on the precision an implementation supports. Weight is not a percentage and the sum of weights does not need to equal 100. If only one backend is specified and it has a weight greater than 0, 100% of the traffic is forwarded to that backend. If weight is set to 0, no traffic should be forwarded for this entry. If unspecified, weight defaults to 1. Support for this field varies based on the context where used. format: int32 maximum: 1000000 minimum: 0 type: integer required: - name type: object x-kubernetes-validations: - message: Must have port for Service reference rule: '(size(self.group) == 0 && self.kind == ''Service'') ? has(self.port) : true' grpcRoutesEnabled: default: false description: GRPCRoutesEnabled is a flag to enable GRPCRoutes for the created gateway. type: boolean httpRoutesEnabled: default: true description: HTTPRoutesEnabled is a flag to enable HTTPRoutes for the created gateway. type: boolean name: description: Name of the gateway minLength: 1 type: string namespace: description: Namespace of the gateway minLength: 1 type: string required: - name - namespace type: object hostDomainName: description: |- HostDomainName is the domain name of the hostname matched by the router. The hostname is constructed as "..", where the a subdomain of the matched hostname. eg. example.com for "..example.com" maxLength: 63 minLength: 1 pattern: ^(([a-z0-9][a-z0-9\-]*[a-z0-9])|[a-z0-9]+\.)*([a-z]+|xn\-\-[a-z0-9]+)\.?$ type: string ingress: description: Ingress is the ingress controller to use for the created ingress. properties: ingressClass: description: IngressClass is the ingress class to use for the created ingress. minLength: 1 type: string tlsSecretName: description: TLSSecretName is the name of the secret containing the TLS certificate and key. type: string required: - ingressClass type: object type: object x-kubernetes-validations: - message: 'unsupported field: spec.expose.router.gateway.grpcRoutesEnabled' rule: '!(has(self.gateway) && self.gateway.grpcRoutesEnabled)' - message: ingress and gateway cannot be specified together rule: '!(has(self.gateway) && has(self.ingress))' service: description: Service defines attributes to create a service. properties: annotations: additionalProperties: type: string type: object grpcPort: description: |- GRPCPort is the GRPC serving port Note: This port is only applicable for NIMs that runs a Triton GRPC Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer metricsPort: description: |- MetricsPort is the port for metrics Note: This port is only applicable for NIMs that runs a separate metrics endpoint on Triton Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer name: description: Override the default service name type: string port: default: 8000 description: 'Port is the main api serving port (default: 8000)' format: int32 maximum: 65535 minimum: 1 type: integer type: description: Service Type string describes ingress methods for a service type: string type: object type: object x-kubernetes-validations: - message: 'unsupported field: spec.expose.service.grpcPort' rule: '!(has(self.service.grpcPort))' - message: 'unsupported field: spec.expose.service.metricsPort' rule: '!(has(self.service.metricsPort))' groupID: format: int64 type: integer image: description: Image defines image attributes. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object labels: additionalProperties: type: string type: object metrics: description: Metrics defines attributes to setup metrics collection. properties: enabled: type: boolean serviceMonitor: description: for use with the Prometheus Operator and the primary service object properties: additionalLabels: additionalProperties: type: string type: object annotations: additionalProperties: type: string type: object interval: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string scrapeTimeout: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string type: object type: object nodeSelector: additionalProperties: type: string type: object objectStoreConfig: description: ObjectStore specifies the location and credentials for accessing the external Object Storage properties: bucketName: description: BucketName is the bucket where LFS files will be stored type: string credentials: description: ObjectStoreCredentials stores the configuration to retrieve the object store credentials properties: passwordKey: description: PasswordKey is the name of the key in the `CredentialsSecret` secret for the object store credentials. type: string secretName: description: SecretName is the name of the secret which has the object credentials for a NEMO service user. type: string user: description: User is the non-root username for a NEMO Service in the object store. type: string required: - passwordKey - secretName - user type: object endpoint: description: endpoint is the fully qualidfied object store endpoint type: string region: description: Region is the region where bucket is hosted type: string serveDirect: default: true type: boolean ssl: description: SSL enable ssl for object store transport type: boolean required: - bucketName - credentials - endpoint - region - ssl type: object podAffinity: description: 'Deprecated: Use Affinity instead.' properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object pvc: description: PVC defines the PersistentVolumeClaim for the datastore properties: annotations: additionalProperties: type: string description: Annotations for the PVC type: object create: description: |- Create specifies whether to create a new PersistentVolumeClaim (PVC). If set to false, an existing PVC must be referenced via the `Name` field. type: boolean name: description: Name of the PVC to use. Required if `Create` is false (i.e., using an existing PVC). type: string size: description: Size of the NIM cache in Gi, used during PVC creation type: string storageClass: description: |- StorageClass to be used for PVC creation. Leave it as empty if the PVC is already created or a default storage class is set in the cluster. type: string subPath: description: SubPath is the path inside the PVC that should be mounted type: string volumeAccessMode: description: VolumeAccessMode is the volume access mode of the PVC type: string type: object replicas: format: int32 minimum: 1 type: integer resources: description: ResourceRequirements describes the compute resource requirements. properties: claims: description: |- Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. This field depends on the DynamicResourceAllocation feature gate. This field is immutable. It can only be set for containers. items: description: ResourceClaim references one entry in PodSpec.ResourceClaims. properties: name: description: |- Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. type: string request: description: |- Request is the name chosen for a request in the referenced claim. If empty, everything from the claim is made available, otherwise only the result of this request. type: string required: - name type: object type: array x-kubernetes-list-map-keys: - name x-kubernetes-list-type: map limits: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object runtimeClass: type: string scale: description: Autoscaling defines attributes to automatically scale the service based on metrics. properties: annotations: additionalProperties: type: string type: object enabled: type: boolean hpa: description: HorizontalPodAutoscalerSpec defines the parameters required to setup HPA. properties: behavior: description: |- HorizontalPodAutoscalerBehavior configures the scaling behavior of the target in both Up and Down directions (scaleUp and scaleDown fields respectively). properties: scaleDown: description: |- scaleDown is scaling policy for scaling Down. If not set, the default value is to allow to scale down to minReplicas pods, with a 300 second stabilization window (i.e., the highest recommendation for the last 300sec is used). properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object scaleUp: description: |- scaleUp is scaling policy for scaling Up. If not set, the default value is the higher of: * increase no more than 4 pods per 60 seconds * double the number of pods per 60 seconds No stabilization is used. properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object type: object maxReplicas: format: int32 type: integer metrics: items: description: |- MetricSpec specifies how to scale based on a single metric (only `type` and one other matching field should be set at once). properties: containerResource: description: |- containerResource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing a single container in each pod of the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: container: description: container is the name of the container in the pods of the scaling target type: string name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - container - name - target type: object external: description: |- external refers to a global metric that is not associated with any Kubernetes object. It allows autoscaling based on information coming from components running outside of cluster (for example length of queue in cloud messaging service, or QPS from loadbalancer running outside of cluster). properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object object: description: |- object refers to a metric describing a single kubernetes object (for example, hits-per-second on an Ingress object). properties: describedObject: description: describedObject specifies the descriptions of a object,such as kind,name apiVersion properties: apiVersion: description: apiVersion is the API version of the referent type: string kind: description: 'kind is the kind of the referent; More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'name is the name of the referent; More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' type: string required: - kind - name type: object metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - describedObject - metric - target type: object pods: description: |- pods refers to a metric describing each pod in the current scale target (for example, transactions-processed-per-second). The values will be averaged together before being compared to the target value. properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object resource: description: |- resource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing each pod in the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - name - target type: object type: description: |- type is the type of metric source. It should be one of "ContainerResource", "External", "Object", "Pods" or "Resource", each mapping to a matching field in the object. type: string required: - type type: object type: array minReplicas: default: 1 format: int32 minimum: 1 type: integer required: - maxReplicas type: object type: object secrets: description: Secrets contains the pre-requisite secrets that must be created before deploying the datastore CR properties: datastoreConfigSecret: type: string datastoreInitSecret: type: string datastoreInlineConfigSecret: type: string giteaAdminSecret: type: string lfsJwtSecret: type: string required: - datastoreConfigSecret - datastoreInitSecret - datastoreInlineConfigSecret - giteaAdminSecret - lfsJwtSecret type: object tolerations: items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array userID: format: int64 type: integer required: - databaseConfig - image - secrets type: object x-kubernetes-validations: - message: .spec.expose.ingress is deprecated, and will be removed in a future release. If .spec.expose.ingress is set, please do not set .spec.expose.router.ingress. rule: '!(has(self.expose.ingress) && has(self.expose.ingress.enabled) && self.expose.ingress.enabled && has(self.expose.router) && has(self.expose.router.ingress))' - message: spec.replicas cannot be set when spec.scale.enabled is true rule: '!(has(self.scale) && has(self.scale.enabled) && self.scale.enabled && has(self.replicas))' status: description: NemoDatastoreStatus defines the observed state of NemoDatastore. properties: availableReplicas: format: int32 type: integer conditions: items: description: Condition contains details for one aspect of the current state of this API Resource. properties: lastTransitionTime: description: |- lastTransitionTime is the last time the condition transitioned from one status to another. This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable. format: date-time type: string message: description: |- message is a human readable message indicating details about the transition. This may be an empty string. maxLength: 32768 type: string observedGeneration: description: |- observedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date with respect to the current state of the instance. format: int64 minimum: 0 type: integer reason: description: |- reason contains a programmatic identifier indicating the reason for the condition's last transition. Producers of specific condition types may define expected values and meanings for this field, and whether the values are considered a guaranteed API. The value should be a CamelCase string. This field may not be empty. maxLength: 1024 minLength: 1 pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$ type: string status: description: status of the condition, one of True, False, Unknown. enum: - "True" - "False" - Unknown type: string type: description: type of condition in CamelCase or in foo.example.com/CamelCase. maxLength: 316 pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$ type: string required: - lastTransitionTime - message - reason - status - type type: object type: array state: type: string type: object type: object served: true storage: true subresources: status: {} --- # Source: k8s-nim-operator/crds/apps.nvidia.com_nemoentitystores.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.0 name: nemoentitystores.apps.nvidia.com spec: group: apps.nvidia.com names: kind: NemoEntitystore listKind: NemoEntitystoreList plural: nemoentitystores singular: nemoentitystore scope: Namespaced versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - format: date-time jsonPath: .metadata.creationTimestamp name: Age type: date name: v1alpha1 schema: openAPIV3Schema: description: NemoEntitystore is the Schema for the NemoEntitystore API. properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string metadata: type: object spec: description: NemoEntitystoreSpec defines the desired state of NemoEntitystore. properties: affinity: description: Affinity is a group of affinity scheduling rules. properties: nodeAffinity: description: Describes node affinity scheduling rules for the pod. properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. items: description: |- An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). properties: preference: description: A node selector term, associated with the corresponding weight. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic weight: description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. format: int32 type: integer required: - preference - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. properties: nodeSelectorTerms: description: Required. A list of node selector terms. The terms are ORed. items: description: |- A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic type: array x-kubernetes-list-type: atomic required: - nodeSelectorTerms type: object x-kubernetes-map-type: atomic type: object podAffinity: description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object podAntiAffinity: description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and subtracting "weight" from the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object type: object annotations: additionalProperties: type: string type: object args: items: type: string type: array command: items: type: string type: array databaseConfig: description: |- DatabaseConfig stores the database configuration for NEMO entitystore. Required, must not be nil. properties: credentials: description: |- DatabaseCredentials stores the configuration to retrieve the database credentials. Required, must not be nil. properties: passwordKey: default: password description: |- PasswordKey is the name of the key in the `CredentialsSecret` secret for the database credentials. Defaults to "password". type: string secretName: description: |- SecretName is the name of the secret which has the database credentials for a NEMO service user. Required, must not be empty. minLength: 1 type: string user: description: |- User is the non-root username for a NEMO Service in the database. Required, must not be empty. minLength: 1 type: string required: - secretName - user type: object databaseName: description: |- DatabaseName is the database name for a NEMO Service. Required, must not be empty. minLength: 1 type: string host: description: |- Host is the hostname of the database. Required, must not be empty. minLength: 1 type: string port: default: 5432 description: |- Port is the port where the database is reachable at. If specified, this must be a valid port number, 0 < databasePort < 65536. Defaults to 5432. format: int32 maximum: 65535 minimum: 1 type: integer required: - credentials - databaseName - host type: object datastore: description: Datastore stores the datastore endpoint. properties: endpoint: minLength: 1 pattern: ^http type: string required: - endpoint type: object env: items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array expose: description: DEPRECATED ExposeV1 defines attributes to expose the service. properties: ingress: description: |- Deprecated: Use .spec.expose.router.ingress instead. IngressV1 defines attributes for ingress properties: annotations: additionalProperties: type: string type: object enabled: type: boolean spec: properties: host: type: string ingressClassName: pattern: '[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*' type: string paths: items: description: IngressPath defines attributes for ingress paths. properties: path: default: / type: string pathType: default: Prefix description: PathType represents the type of path referred to by a HTTPIngressPath. type: string type: object type: array required: - ingressClassName type: object type: object x-kubernetes-validations: - message: spec cannot be nil when ingress is enabled rule: (has(self.spec) && has(self.enabled) && self.enabled) || !has(self.enabled) || !self.enabled router: properties: annotations: additionalProperties: type: string description: Annotations for the router, e.g. for ingress class or gateway type: object eppConfig: description: EPPConfig is the configuration for the endpoint picker extension. This is field is currently only supported for standalone inference platform only on NIMService. properties: config: description: |- Config allows specifying EPP EndpointPickerConfig directly as a structured object. The operator will marshal this to YAML and create a ConfigMap automatically. Mutually exclusive with ConfigMapRef. One of ConfigMapRef or Config must be specified (no default configuration). Uses the upstream type from github.com/kubernetes-sigs/gateway-api-inference-extension properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string data: description: Data configures the DataLayer. It is required if the new DataLayer is enabled. properties: sources: description: Sources is the list of sources to define to the DataLayer items: description: DataLayerSource contains the configuration of a DataSource of the DataLayer feature properties: extractors: description: |- Extractors specifies the list of Plugin instances to be associated with this Source. The entries are references to the names of entries of the Plugins defined in the configuration's Plugins section items: description: DataLayerExtractor contains the configuration of an Extractor of the DataLayer feature properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Extractor. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - pluginRef type: object type: array pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Source. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - extractors - pluginRef type: object type: array required: - sources type: object featureGates: description: |- FeatureGates is a set of flags that enable various experimental features with the EPP. If omitted non of these experimental features will be enabled. items: type: string type: array kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string plugins: description: Plugins is the list of plugins that will be instantiated. items: description: |- PluginSpec contains the information that describes a plugin that will be instantiated. properties: name: description: |- Name provides a name for plugin entries to reference. If omitted, the value of the Plugin's Type field will be used. type: string parameters: description: |- Parameters are the set of parameters to be passed to the plugin's factory function. The factory function is responsible to parse the parameters. format: byte type: string type: description: Type specifies the plugin type to be instantiated. type: string required: - type type: object type: array saturationDetector: description: |- SaturationDetector when present specifies the configuration of the Saturation detector. If not present, default values are used. properties: kvCacheUtilThreshold: description: |- KVCacheUtilThreshold defines the KV cache utilization (0.0 to 1.0) above which a pod is considered to have insufficient capacity. type: number metricsStalenessThreshold: description: |- MetricsStalenessThreshold defines how old a pod's metrics can be. If a pod's metrics are older than this, it might be excluded from "good capacity" considerations or treated as having no capacity for safety. type: string queueDepthThreshold: description: |- QueueDepthThreshold defines the backend waiting queue size above which a pod is considered to have insufficient capacity for new requests. type: integer type: object schedulingProfiles: description: |- SchedulingProfiles is the list of named SchedulingProfiles that will be created. items: description: |- SchedulingProfile contains the information to create a SchedulingProfile entry to be used by the scheduler. properties: name: description: Name specifies the name of this SchedulingProfile type: string plugins: description: |- Plugins is the list of plugins for this SchedulingProfile. They are assigned to the appropriate "slots" based on their type. items: description: |- SchedulingPlugin describes a plugin that will be associated with a SchedulingProfile entry. properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this SchedulingProfile. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string weight: description: Weight is the weight fo be used if this plugin is a Scorer. type: integer required: - pluginRef type: object type: array required: - name - plugins type: object type: array required: - plugins - schedulingProfiles type: object x-kubernetes-preserve-unknown-fields: true configMapRef: description: |- ConfigMapRef references a user-provided ConfigMap containing EPP configuration. The ConfigMap should contain EndpointPickerConfig YAML. Mutually exclusive with Config. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic containerSpec: description: ContainerSpec is the specification for the EPP container. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object livenessProbe: description: LivenessProbe is the liveness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object ports: description: Ports is the list of ports to expose for the EPP container. items: description: ContainerPort represents a network port in a single container. properties: containerPort: description: |- Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. format: int32 type: integer hostIP: description: What host IP to bind the external port to. type: string hostPort: description: |- Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. format: int32 type: integer name: description: |- If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. type: string protocol: default: TCP description: |- Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". type: string required: - containerPort type: object type: array readinessProbe: description: ReadinessProbe is the readiness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object startupProbe: description: StartupProbe is the startup probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object required: - containerSpec type: object x-kubernetes-validations: - message: specify either configMapRef or config, not both rule: '!(has(self.configMapRef) && has(self.config))' gateway: description: Gateway is the gateway to use for the created HTTPRoute. properties: backendRef: description: BackendRef is a reference to a backend to forward matched requests to. properties: group: default: "" description: |- Group is the group of the referent. For example, "gateway.networking.k8s.io". When unspecified or empty string, core API group is inferred. maxLength: 253 pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ type: string kind: default: Service description: |- Kind is the Kubernetes resource kind of the referent. For example "Service". Defaults to "Service" when not specified. ExternalName services can refer to CNAME DNS records that may live outside of the cluster and as such are difficult to reason about in terms of conformance. They also may not be safe to forward to (see CVE-2021-25740 for more information). Implementations SHOULD NOT support ExternalName Services. Support: Core (Services with a type other than ExternalName) Support: Implementation-specific (Services with type ExternalName) maxLength: 63 minLength: 1 pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$ type: string name: description: Name is the name of the referent. maxLength: 253 minLength: 1 type: string namespace: description: |- Namespace is the namespace of the backend. When unspecified, the local namespace is inferred. Note that when a namespace different than the local namespace is specified, a ReferenceGrant object is required in the referent namespace to allow that namespace's owner to accept the reference. See the ReferenceGrant documentation for details. Support: Core maxLength: 63 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ type: string port: description: |- Port specifies the destination port number to use for this resource. Port is required when the referent is a Kubernetes Service. In this case, the port number is the service port number, not the target port. For other resources, destination port might be derived from the referent resource or this field. format: int32 maximum: 65535 minimum: 1 type: integer weight: default: 1 description: |- Weight specifies the proportion of requests forwarded to the referenced backend. This is computed as weight/(sum of all weights in this BackendRefs list). For non-zero values, there may be some epsilon from the exact proportion defined here depending on the precision an implementation supports. Weight is not a percentage and the sum of weights does not need to equal 100. If only one backend is specified and it has a weight greater than 0, 100% of the traffic is forwarded to that backend. If weight is set to 0, no traffic should be forwarded for this entry. If unspecified, weight defaults to 1. Support for this field varies based on the context where used. format: int32 maximum: 1000000 minimum: 0 type: integer required: - name type: object x-kubernetes-validations: - message: Must have port for Service reference rule: '(size(self.group) == 0 && self.kind == ''Service'') ? has(self.port) : true' grpcRoutesEnabled: default: false description: GRPCRoutesEnabled is a flag to enable GRPCRoutes for the created gateway. type: boolean httpRoutesEnabled: default: true description: HTTPRoutesEnabled is a flag to enable HTTPRoutes for the created gateway. type: boolean name: description: Name of the gateway minLength: 1 type: string namespace: description: Namespace of the gateway minLength: 1 type: string required: - name - namespace type: object hostDomainName: description: |- HostDomainName is the domain name of the hostname matched by the router. The hostname is constructed as "..", where the a subdomain of the matched hostname. eg. example.com for "..example.com" maxLength: 63 minLength: 1 pattern: ^(([a-z0-9][a-z0-9\-]*[a-z0-9])|[a-z0-9]+\.)*([a-z]+|xn\-\-[a-z0-9]+)\.?$ type: string ingress: description: Ingress is the ingress controller to use for the created ingress. properties: ingressClass: description: IngressClass is the ingress class to use for the created ingress. minLength: 1 type: string tlsSecretName: description: TLSSecretName is the name of the secret containing the TLS certificate and key. type: string required: - ingressClass type: object type: object x-kubernetes-validations: - message: 'unsupported field: spec.expose.router.gateway.grpcRoutesEnabled' rule: '!(has(self.gateway) && self.gateway.grpcRoutesEnabled)' - message: ingress and gateway cannot be specified together rule: '!(has(self.gateway) && has(self.ingress))' service: description: Service defines attributes to create a service. properties: annotations: additionalProperties: type: string type: object grpcPort: description: |- GRPCPort is the GRPC serving port Note: This port is only applicable for NIMs that runs a Triton GRPC Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer metricsPort: description: |- MetricsPort is the port for metrics Note: This port is only applicable for NIMs that runs a separate metrics endpoint on Triton Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer name: description: Override the default service name type: string port: default: 8000 description: 'Port is the main api serving port (default: 8000)' format: int32 maximum: 65535 minimum: 1 type: integer type: description: Service Type string describes ingress methods for a service type: string type: object type: object x-kubernetes-validations: - message: 'unsupported field: spec.expose.service.grpcPort' rule: '!(has(self.service.grpcPort))' - message: 'unsupported field: spec.expose.service.metricsPort' rule: '!(has(self.service.metricsPort))' groupID: format: int64 type: integer image: description: Image defines image attributes. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object labels: additionalProperties: type: string type: object metrics: description: Metrics defines attributes to setup metrics collection. properties: enabled: type: boolean serviceMonitor: description: for use with the Prometheus Operator and the primary service object properties: additionalLabels: additionalProperties: type: string type: object annotations: additionalProperties: type: string type: object interval: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string scrapeTimeout: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string type: object type: object nodeSelector: additionalProperties: type: string type: object podAffinity: description: 'Deprecated: Use Affinity instead.' properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object replicas: format: int32 minimum: 1 type: integer resources: description: ResourceRequirements describes the compute resource requirements. properties: claims: description: |- Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. This field depends on the DynamicResourceAllocation feature gate. This field is immutable. It can only be set for containers. items: description: ResourceClaim references one entry in PodSpec.ResourceClaims. properties: name: description: |- Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. type: string request: description: |- Request is the name chosen for a request in the referenced claim. If empty, everything from the claim is made available, otherwise only the result of this request. type: string required: - name type: object type: array x-kubernetes-list-map-keys: - name x-kubernetes-list-type: map limits: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object runtimeClass: type: string scale: description: Autoscaling defines attributes to automatically scale the service based on metrics. properties: annotations: additionalProperties: type: string type: object enabled: type: boolean hpa: description: HorizontalPodAutoscalerSpec defines the parameters required to setup HPA. properties: behavior: description: |- HorizontalPodAutoscalerBehavior configures the scaling behavior of the target in both Up and Down directions (scaleUp and scaleDown fields respectively). properties: scaleDown: description: |- scaleDown is scaling policy for scaling Down. If not set, the default value is to allow to scale down to minReplicas pods, with a 300 second stabilization window (i.e., the highest recommendation for the last 300sec is used). properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object scaleUp: description: |- scaleUp is scaling policy for scaling Up. If not set, the default value is the higher of: * increase no more than 4 pods per 60 seconds * double the number of pods per 60 seconds No stabilization is used. properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object type: object maxReplicas: format: int32 type: integer metrics: items: description: |- MetricSpec specifies how to scale based on a single metric (only `type` and one other matching field should be set at once). properties: containerResource: description: |- containerResource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing a single container in each pod of the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: container: description: container is the name of the container in the pods of the scaling target type: string name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - container - name - target type: object external: description: |- external refers to a global metric that is not associated with any Kubernetes object. It allows autoscaling based on information coming from components running outside of cluster (for example length of queue in cloud messaging service, or QPS from loadbalancer running outside of cluster). properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object object: description: |- object refers to a metric describing a single kubernetes object (for example, hits-per-second on an Ingress object). properties: describedObject: description: describedObject specifies the descriptions of a object,such as kind,name apiVersion properties: apiVersion: description: apiVersion is the API version of the referent type: string kind: description: 'kind is the kind of the referent; More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'name is the name of the referent; More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' type: string required: - kind - name type: object metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - describedObject - metric - target type: object pods: description: |- pods refers to a metric describing each pod in the current scale target (for example, transactions-processed-per-second). The values will be averaged together before being compared to the target value. properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object resource: description: |- resource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing each pod in the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - name - target type: object type: description: |- type is the type of metric source. It should be one of "ContainerResource", "External", "Object", "Pods" or "Resource", each mapping to a matching field in the object. type: string required: - type type: object type: array minReplicas: default: 1 format: int32 minimum: 1 type: integer required: - maxReplicas type: object type: object tolerations: items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array userID: format: int64 type: integer required: - databaseConfig - datastore - image type: object x-kubernetes-validations: - message: .spec.expose.ingress is deprecated, and will be removed in a future release. If .spec.expose.ingress is set, please do not set .spec.expose.router.ingress. rule: '!(has(self.expose.ingress) && has(self.expose.ingress.enabled) && self.expose.ingress.enabled && has(self.expose.router) && has(self.expose.router.ingress))' - message: spec.replicas cannot be set when spec.scale.enabled is true rule: '!(has(self.scale) && has(self.scale.enabled) && self.scale.enabled && has(self.replicas))' status: description: NemoEntitystoreStatus defines the observed state of NemoEntitystore. properties: availableReplicas: format: int32 type: integer conditions: items: description: Condition contains details for one aspect of the current state of this API Resource. properties: lastTransitionTime: description: |- lastTransitionTime is the last time the condition transitioned from one status to another. This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable. format: date-time type: string message: description: |- message is a human readable message indicating details about the transition. This may be an empty string. maxLength: 32768 type: string observedGeneration: description: |- observedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date with respect to the current state of the instance. format: int64 minimum: 0 type: integer reason: description: |- reason contains a programmatic identifier indicating the reason for the condition's last transition. Producers of specific condition types may define expected values and meanings for this field, and whether the values are considered a guaranteed API. The value should be a CamelCase string. This field may not be empty. maxLength: 1024 minLength: 1 pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$ type: string status: description: status of the condition, one of True, False, Unknown. enum: - "True" - "False" - Unknown type: string type: description: type of condition in CamelCase or in foo.example.com/CamelCase. maxLength: 316 pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$ type: string required: - lastTransitionTime - message - reason - status - type type: object type: array state: type: string type: object type: object served: true storage: true subresources: status: {} --- # Source: k8s-nim-operator/crds/apps.nvidia.com_nemoevaluators.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.0 name: nemoevaluators.apps.nvidia.com spec: group: apps.nvidia.com names: kind: NemoEvaluator listKind: NemoEvaluatorList plural: nemoevaluators singular: nemoevaluator scope: Namespaced versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - format: date-time jsonPath: .metadata.creationTimestamp name: Age type: date name: v1alpha1 schema: openAPIV3Schema: description: NemoEvaluator is the Schema for the NemoEvaluator API. properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string metadata: type: object spec: description: NemoEvaluatorSpec defines the desired state of NemoEvaluator. properties: affinity: description: Affinity is a group of affinity scheduling rules. properties: nodeAffinity: description: Describes node affinity scheduling rules for the pod. properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. items: description: |- An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). properties: preference: description: A node selector term, associated with the corresponding weight. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic weight: description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. format: int32 type: integer required: - preference - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. properties: nodeSelectorTerms: description: Required. A list of node selector terms. The terms are ORed. items: description: |- A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic type: array x-kubernetes-list-type: atomic required: - nodeSelectorTerms type: object x-kubernetes-map-type: atomic type: object podAffinity: description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object podAntiAffinity: description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and subtracting "weight" from the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object type: object annotations: additionalProperties: type: string type: object argoWorkflows: description: ArgoWorkflows stores the argo workflow service endpoint. properties: endpoint: minLength: 1 pattern: ^http type: string serviceAccount: type: string required: - endpoint - serviceAccount type: object args: items: type: string type: array command: items: type: string type: array consoleLogLevel: default: INFO description: ConsoleLogLevel defines the console log level (e.g., INFO, DEBUG). enum: - INFO - DEBUG type: string databaseConfig: description: DatabaseConfig stores the database configuration for NeMo entitystore. properties: credentials: description: |- DatabaseCredentials stores the configuration to retrieve the database credentials. Required, must not be nil. properties: passwordKey: default: password description: |- PasswordKey is the name of the key in the `CredentialsSecret` secret for the database credentials. Defaults to "password". type: string secretName: description: |- SecretName is the name of the secret which has the database credentials for a NEMO service user. Required, must not be empty. minLength: 1 type: string user: description: |- User is the non-root username for a NEMO Service in the database. Required, must not be empty. minLength: 1 type: string required: - secretName - user type: object databaseName: description: |- DatabaseName is the database name for a NEMO Service. Required, must not be empty. minLength: 1 type: string host: description: |- Host is the hostname of the database. Required, must not be empty. minLength: 1 type: string port: default: 5432 description: |- Port is the port where the database is reachable at. If specified, this must be a valid port number, 0 < databasePort < 65536. Defaults to 5432. format: int32 maximum: 65535 minimum: 1 type: integer required: - credentials - databaseName - host type: object datastore: description: Datastore stores the datastore endpoint. properties: endpoint: minLength: 1 pattern: ^http type: string required: - endpoint type: object enableValidation: description: EnableValidation indicates that the validation jobs to be enabled type: boolean entitystore: description: Entitystore stores the entitystore endpoint. properties: endpoint: minLength: 1 pattern: ^http type: string required: - endpoint type: object env: items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array evalLogLevel: default: INFO description: EvalLogLevel defines the evaluator log level (e.g., INFO, DEBUG). enum: - INFO - DEBUG type: string evaluationImages: description: EvaluationImages defines the external images used for evaluation properties: agenticEval: type: string bfcl: type: string bigcodeEvalHarness: type: string llmAsJudge: type: string lmEvalHarness: type: string mtBench: type: string rag: type: string retriever: type: string similarityMetrics: type: string type: object expose: description: DEPRECATED ExposeV1 defines attributes to expose the service. properties: ingress: description: |- Deprecated: Use .spec.expose.router.ingress instead. IngressV1 defines attributes for ingress properties: annotations: additionalProperties: type: string type: object enabled: type: boolean spec: properties: host: type: string ingressClassName: pattern: '[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*' type: string paths: items: description: IngressPath defines attributes for ingress paths. properties: path: default: / type: string pathType: default: Prefix description: PathType represents the type of path referred to by a HTTPIngressPath. type: string type: object type: array required: - ingressClassName type: object type: object x-kubernetes-validations: - message: spec cannot be nil when ingress is enabled rule: (has(self.spec) && has(self.enabled) && self.enabled) || !has(self.enabled) || !self.enabled router: properties: annotations: additionalProperties: type: string description: Annotations for the router, e.g. for ingress class or gateway type: object eppConfig: description: EPPConfig is the configuration for the endpoint picker extension. This is field is currently only supported for standalone inference platform only on NIMService. properties: config: description: |- Config allows specifying EPP EndpointPickerConfig directly as a structured object. The operator will marshal this to YAML and create a ConfigMap automatically. Mutually exclusive with ConfigMapRef. One of ConfigMapRef or Config must be specified (no default configuration). Uses the upstream type from github.com/kubernetes-sigs/gateway-api-inference-extension properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string data: description: Data configures the DataLayer. It is required if the new DataLayer is enabled. properties: sources: description: Sources is the list of sources to define to the DataLayer items: description: DataLayerSource contains the configuration of a DataSource of the DataLayer feature properties: extractors: description: |- Extractors specifies the list of Plugin instances to be associated with this Source. The entries are references to the names of entries of the Plugins defined in the configuration's Plugins section items: description: DataLayerExtractor contains the configuration of an Extractor of the DataLayer feature properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Extractor. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - pluginRef type: object type: array pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Source. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - extractors - pluginRef type: object type: array required: - sources type: object featureGates: description: |- FeatureGates is a set of flags that enable various experimental features with the EPP. If omitted non of these experimental features will be enabled. items: type: string type: array kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string plugins: description: Plugins is the list of plugins that will be instantiated. items: description: |- PluginSpec contains the information that describes a plugin that will be instantiated. properties: name: description: |- Name provides a name for plugin entries to reference. If omitted, the value of the Plugin's Type field will be used. type: string parameters: description: |- Parameters are the set of parameters to be passed to the plugin's factory function. The factory function is responsible to parse the parameters. format: byte type: string type: description: Type specifies the plugin type to be instantiated. type: string required: - type type: object type: array saturationDetector: description: |- SaturationDetector when present specifies the configuration of the Saturation detector. If not present, default values are used. properties: kvCacheUtilThreshold: description: |- KVCacheUtilThreshold defines the KV cache utilization (0.0 to 1.0) above which a pod is considered to have insufficient capacity. type: number metricsStalenessThreshold: description: |- MetricsStalenessThreshold defines how old a pod's metrics can be. If a pod's metrics are older than this, it might be excluded from "good capacity" considerations or treated as having no capacity for safety. type: string queueDepthThreshold: description: |- QueueDepthThreshold defines the backend waiting queue size above which a pod is considered to have insufficient capacity for new requests. type: integer type: object schedulingProfiles: description: |- SchedulingProfiles is the list of named SchedulingProfiles that will be created. items: description: |- SchedulingProfile contains the information to create a SchedulingProfile entry to be used by the scheduler. properties: name: description: Name specifies the name of this SchedulingProfile type: string plugins: description: |- Plugins is the list of plugins for this SchedulingProfile. They are assigned to the appropriate "slots" based on their type. items: description: |- SchedulingPlugin describes a plugin that will be associated with a SchedulingProfile entry. properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this SchedulingProfile. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string weight: description: Weight is the weight fo be used if this plugin is a Scorer. type: integer required: - pluginRef type: object type: array required: - name - plugins type: object type: array required: - plugins - schedulingProfiles type: object x-kubernetes-preserve-unknown-fields: true configMapRef: description: |- ConfigMapRef references a user-provided ConfigMap containing EPP configuration. The ConfigMap should contain EndpointPickerConfig YAML. Mutually exclusive with Config. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic containerSpec: description: ContainerSpec is the specification for the EPP container. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object livenessProbe: description: LivenessProbe is the liveness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object ports: description: Ports is the list of ports to expose for the EPP container. items: description: ContainerPort represents a network port in a single container. properties: containerPort: description: |- Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. format: int32 type: integer hostIP: description: What host IP to bind the external port to. type: string hostPort: description: |- Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. format: int32 type: integer name: description: |- If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. type: string protocol: default: TCP description: |- Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". type: string required: - containerPort type: object type: array readinessProbe: description: ReadinessProbe is the readiness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object startupProbe: description: StartupProbe is the startup probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object required: - containerSpec type: object x-kubernetes-validations: - message: specify either configMapRef or config, not both rule: '!(has(self.configMapRef) && has(self.config))' gateway: description: Gateway is the gateway to use for the created HTTPRoute. properties: backendRef: description: BackendRef is a reference to a backend to forward matched requests to. properties: group: default: "" description: |- Group is the group of the referent. For example, "gateway.networking.k8s.io". When unspecified or empty string, core API group is inferred. maxLength: 253 pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ type: string kind: default: Service description: |- Kind is the Kubernetes resource kind of the referent. For example "Service". Defaults to "Service" when not specified. ExternalName services can refer to CNAME DNS records that may live outside of the cluster and as such are difficult to reason about in terms of conformance. They also may not be safe to forward to (see CVE-2021-25740 for more information). Implementations SHOULD NOT support ExternalName Services. Support: Core (Services with a type other than ExternalName) Support: Implementation-specific (Services with type ExternalName) maxLength: 63 minLength: 1 pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$ type: string name: description: Name is the name of the referent. maxLength: 253 minLength: 1 type: string namespace: description: |- Namespace is the namespace of the backend. When unspecified, the local namespace is inferred. Note that when a namespace different than the local namespace is specified, a ReferenceGrant object is required in the referent namespace to allow that namespace's owner to accept the reference. See the ReferenceGrant documentation for details. Support: Core maxLength: 63 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ type: string port: description: |- Port specifies the destination port number to use for this resource. Port is required when the referent is a Kubernetes Service. In this case, the port number is the service port number, not the target port. For other resources, destination port might be derived from the referent resource or this field. format: int32 maximum: 65535 minimum: 1 type: integer weight: default: 1 description: |- Weight specifies the proportion of requests forwarded to the referenced backend. This is computed as weight/(sum of all weights in this BackendRefs list). For non-zero values, there may be some epsilon from the exact proportion defined here depending on the precision an implementation supports. Weight is not a percentage and the sum of weights does not need to equal 100. If only one backend is specified and it has a weight greater than 0, 100% of the traffic is forwarded to that backend. If weight is set to 0, no traffic should be forwarded for this entry. If unspecified, weight defaults to 1. Support for this field varies based on the context where used. format: int32 maximum: 1000000 minimum: 0 type: integer required: - name type: object x-kubernetes-validations: - message: Must have port for Service reference rule: '(size(self.group) == 0 && self.kind == ''Service'') ? has(self.port) : true' grpcRoutesEnabled: default: false description: GRPCRoutesEnabled is a flag to enable GRPCRoutes for the created gateway. type: boolean httpRoutesEnabled: default: true description: HTTPRoutesEnabled is a flag to enable HTTPRoutes for the created gateway. type: boolean name: description: Name of the gateway minLength: 1 type: string namespace: description: Namespace of the gateway minLength: 1 type: string required: - name - namespace type: object hostDomainName: description: |- HostDomainName is the domain name of the hostname matched by the router. The hostname is constructed as "..", where the a subdomain of the matched hostname. eg. example.com for "..example.com" maxLength: 63 minLength: 1 pattern: ^(([a-z0-9][a-z0-9\-]*[a-z0-9])|[a-z0-9]+\.)*([a-z]+|xn\-\-[a-z0-9]+)\.?$ type: string ingress: description: Ingress is the ingress controller to use for the created ingress. properties: ingressClass: description: IngressClass is the ingress class to use for the created ingress. minLength: 1 type: string tlsSecretName: description: TLSSecretName is the name of the secret containing the TLS certificate and key. type: string required: - ingressClass type: object type: object x-kubernetes-validations: - message: 'unsupported field: spec.expose.router.gateway.grpcRoutesEnabled' rule: '!(has(self.gateway) && self.gateway.grpcRoutesEnabled)' - message: ingress and gateway cannot be specified together rule: '!(has(self.gateway) && has(self.ingress))' service: description: Service defines attributes to create a service. properties: annotations: additionalProperties: type: string type: object grpcPort: description: |- GRPCPort is the GRPC serving port Note: This port is only applicable for NIMs that runs a Triton GRPC Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer metricsPort: description: |- MetricsPort is the port for metrics Note: This port is only applicable for NIMs that runs a separate metrics endpoint on Triton Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer name: description: Override the default service name type: string port: default: 8000 description: 'Port is the main api serving port (default: 8000)' format: int32 maximum: 65535 minimum: 1 type: integer type: description: Service Type string describes ingress methods for a service type: string type: object type: object x-kubernetes-validations: - message: 'unsupported field: spec.expose.service.grpcPort' rule: '!(has(self.service.grpcPort))' - message: 'unsupported field: spec.expose.service.metricsPort' rule: '!(has(self.service.metricsPort))' groupID: format: int64 type: integer image: description: Image defines image attributes. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object labels: additionalProperties: type: string description: The name of an secret that contains authn for the NGC NIM service API type: object logHandlers: default: console description: LogHandlers defines the log sink handlers (e.g., INFO, DEBUG). enum: - console - file type: string metrics: description: Metrics defines attributes to setup metrics collection. properties: enabled: type: boolean serviceMonitor: description: for use with the Prometheus Operator and the primary service object properties: additionalLabels: additionalProperties: type: string type: object annotations: additionalProperties: type: string type: object interval: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string scrapeTimeout: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string type: object type: object nodeSelector: additionalProperties: type: string type: object otel: description: OpenTelemetry Settings properties: disableLogging: description: DisableLogging indicates whether Python logging auto-instrumentation should be disabled. type: boolean enabled: description: Enabled indicates if opentelemetry collector and tracing are enabled type: boolean excludedUrls: default: - health description: ExcludedUrls defines URLs to be excluded from tracing. items: type: string type: array exporterConfig: description: ExporterConfig defines configuration for different OTel exporters properties: logsExporter: default: otlp description: 'LogsExporter sets the logs exporter: (otlp, console, none).' enum: - otlp - console - none type: string metricsExporter: default: otlp description: 'MetricsExporter sets the metrics exporter: (otlp, console, none).' enum: - otlp - console - none type: string tracesExporter: default: otlp description: 'TracesExporter sets the traces exporter: (otlp, console, none).' enum: - otlp - console - none type: string type: object exporterOtlpEndpoint: description: ExporterOtlpEndpoint is the OTLP collector endpoint. type: string logLevel: default: INFO description: LogLevel defines the log level (e.g., INFO, DEBUG). enum: - INFO - DEBUG type: string type: object podAffinity: description: 'Deprecated: Use Affinity instead.' properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object replicas: format: int32 minimum: 1 type: integer resources: description: ResourceRequirements describes the compute resource requirements. properties: claims: description: |- Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. This field depends on the DynamicResourceAllocation feature gate. This field is immutable. It can only be set for containers. items: description: ResourceClaim references one entry in PodSpec.ResourceClaims. properties: name: description: |- Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. type: string request: description: |- Request is the name chosen for a request in the referenced claim. If empty, everything from the claim is made available, otherwise only the result of this request. type: string required: - name type: object type: array x-kubernetes-list-map-keys: - name x-kubernetes-list-type: map limits: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object runtimeClass: type: string scale: description: Autoscaling defines attributes to automatically scale the service based on metrics. properties: annotations: additionalProperties: type: string type: object enabled: type: boolean hpa: description: HorizontalPodAutoscalerSpec defines the parameters required to setup HPA. properties: behavior: description: |- HorizontalPodAutoscalerBehavior configures the scaling behavior of the target in both Up and Down directions (scaleUp and scaleDown fields respectively). properties: scaleDown: description: |- scaleDown is scaling policy for scaling Down. If not set, the default value is to allow to scale down to minReplicas pods, with a 300 second stabilization window (i.e., the highest recommendation for the last 300sec is used). properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object scaleUp: description: |- scaleUp is scaling policy for scaling Up. If not set, the default value is the higher of: * increase no more than 4 pods per 60 seconds * double the number of pods per 60 seconds No stabilization is used. properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object type: object maxReplicas: format: int32 type: integer metrics: items: description: |- MetricSpec specifies how to scale based on a single metric (only `type` and one other matching field should be set at once). properties: containerResource: description: |- containerResource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing a single container in each pod of the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: container: description: container is the name of the container in the pods of the scaling target type: string name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - container - name - target type: object external: description: |- external refers to a global metric that is not associated with any Kubernetes object. It allows autoscaling based on information coming from components running outside of cluster (for example length of queue in cloud messaging service, or QPS from loadbalancer running outside of cluster). properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object object: description: |- object refers to a metric describing a single kubernetes object (for example, hits-per-second on an Ingress object). properties: describedObject: description: describedObject specifies the descriptions of a object,such as kind,name apiVersion properties: apiVersion: description: apiVersion is the API version of the referent type: string kind: description: 'kind is the kind of the referent; More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'name is the name of the referent; More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' type: string required: - kind - name type: object metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - describedObject - metric - target type: object pods: description: |- pods refers to a metric describing each pod in the current scale target (for example, transactions-processed-per-second). The values will be averaged together before being compared to the target value. properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object resource: description: |- resource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing each pod in the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - name - target type: object type: description: |- type is the type of metric source. It should be one of "ContainerResource", "External", "Object", "Pods" or "Resource", each mapping to a matching field in the object. type: string required: - type type: object type: array minReplicas: default: 1 format: int32 minimum: 1 type: integer required: - maxReplicas type: object type: object tolerations: items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array userID: format: int64 type: integer vectorDB: description: VectorDB stores the vector db endpoint. properties: endpoint: minLength: 1 pattern: ^http type: string required: - endpoint type: object required: - argoWorkflows - databaseConfig - datastore - entitystore - evaluationImages - image - vectorDB type: object x-kubernetes-validations: - message: .spec.expose.ingress is deprecated, and will be removed in a future release. If .spec.expose.ingress is set, please do not set .spec.expose.router.ingress. rule: '!(has(self.expose.ingress) && has(self.expose.ingress.enabled) && self.expose.ingress.enabled && has(self.expose.router) && has(self.expose.router.ingress))' - message: spec.replicas cannot be set when spec.scale.enabled is true rule: '!(has(self.scale) && has(self.scale.enabled) && self.scale.enabled && has(self.replicas))' status: description: NemoEvaluatorStatus defines the observed state of NemoEvaluator. properties: availableReplicas: format: int32 type: integer conditions: items: description: Condition contains details for one aspect of the current state of this API Resource. properties: lastTransitionTime: description: |- lastTransitionTime is the last time the condition transitioned from one status to another. This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable. format: date-time type: string message: description: |- message is a human readable message indicating details about the transition. This may be an empty string. maxLength: 32768 type: string observedGeneration: description: |- observedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date with respect to the current state of the instance. format: int64 minimum: 0 type: integer reason: description: |- reason contains a programmatic identifier indicating the reason for the condition's last transition. Producers of specific condition types may define expected values and meanings for this field, and whether the values are considered a guaranteed API. The value should be a CamelCase string. This field may not be empty. maxLength: 1024 minLength: 1 pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$ type: string status: description: status of the condition, one of True, False, Unknown. enum: - "True" - "False" - Unknown type: string type: description: type of condition in CamelCase or in foo.example.com/CamelCase. maxLength: 316 pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$ type: string required: - lastTransitionTime - message - reason - status - type type: object type: array state: type: string type: object type: object served: true storage: true subresources: status: {} --- # Source: k8s-nim-operator/crds/apps.nvidia.com_nemoguardrails.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.0 name: nemoguardrails.apps.nvidia.com spec: group: apps.nvidia.com names: kind: NemoGuardrail listKind: NemoGuardrailList plural: nemoguardrails singular: nemoguardrail scope: Namespaced versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - format: date-time jsonPath: .metadata.creationTimestamp name: Age type: date name: v1alpha1 schema: openAPIV3Schema: description: NemoGuardrail is the Schema for the NemoGuardrail API. properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string metadata: type: object spec: description: NemoGuardrailSpec defines the desired state of NemoGuardrail. properties: affinity: description: Affinity is a group of affinity scheduling rules. properties: nodeAffinity: description: Describes node affinity scheduling rules for the pod. properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. items: description: |- An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). properties: preference: description: A node selector term, associated with the corresponding weight. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic weight: description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. format: int32 type: integer required: - preference - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. properties: nodeSelectorTerms: description: Required. A list of node selector terms. The terms are ORed. items: description: |- A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic type: array x-kubernetes-list-type: atomic required: - nodeSelectorTerms type: object x-kubernetes-map-type: atomic type: object podAffinity: description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object podAntiAffinity: description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and subtracting "weight" from the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object type: object annotations: additionalProperties: type: string type: object args: items: type: string type: array command: items: type: string type: array configStore: description: ConfigStore stores the config of the guardrail service properties: configMap: description: ConfigMapRef with a valid config map name. properties: name: minLength: 1 type: string required: - name type: object pvc: description: PersistentVolumeClaim defines the attributes of PVC. properties: annotations: additionalProperties: type: string description: Annotations for the PVC type: object create: description: |- Create specifies whether to create a new PersistentVolumeClaim (PVC). If set to false, an existing PVC must be referenced via the `Name` field. type: boolean name: description: Name of the PVC to use. Required if `Create` is false (i.e., using an existing PVC). type: string size: description: Size of the NIM cache in Gi, used during PVC creation type: string storageClass: description: |- StorageClass to be used for PVC creation. Leave it as empty if the PVC is already created or a default storage class is set in the cluster. type: string subPath: description: SubPath is the path inside the PVC that should be mounted type: string volumeAccessMode: description: VolumeAccessMode is the volume access mode of the PVC type: string type: object type: object x-kubernetes-validations: - message: Cannot set both ConfigMap and PVC in ConfigStore rule: '!(has(self.configMap) && has(self.pvc))' databaseConfig: description: DatabaseConfig stores the metadata for the guardrail service. properties: credentials: description: |- DatabaseCredentials stores the configuration to retrieve the database credentials. Required, must not be nil. properties: passwordKey: default: password description: |- PasswordKey is the name of the key in the `CredentialsSecret` secret for the database credentials. Defaults to "password". type: string secretName: description: |- SecretName is the name of the secret which has the database credentials for a NEMO service user. Required, must not be empty. minLength: 1 type: string user: description: |- User is the non-root username for a NEMO Service in the database. Required, must not be empty. minLength: 1 type: string required: - secretName - user type: object databaseName: description: |- DatabaseName is the database name for a NEMO Service. Required, must not be empty. minLength: 1 type: string host: description: |- Host is the hostname of the database. Required, must not be empty. minLength: 1 type: string port: default: 5432 description: |- Port is the port where the database is reachable at. If specified, this must be a valid port number, 0 < databasePort < 65536. Defaults to 5432. format: int32 maximum: 65535 minimum: 1 type: integer required: - credentials - databaseName - host type: object env: items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array expose: description: DEPRECATED ExposeV1 defines attributes to expose the service. properties: ingress: description: |- Deprecated: Use .spec.expose.router.ingress instead. IngressV1 defines attributes for ingress properties: annotations: additionalProperties: type: string type: object enabled: type: boolean spec: properties: host: type: string ingressClassName: pattern: '[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*' type: string paths: items: description: IngressPath defines attributes for ingress paths. properties: path: default: / type: string pathType: default: Prefix description: PathType represents the type of path referred to by a HTTPIngressPath. type: string type: object type: array required: - ingressClassName type: object type: object x-kubernetes-validations: - message: spec cannot be nil when ingress is enabled rule: (has(self.spec) && has(self.enabled) && self.enabled) || !has(self.enabled) || !self.enabled router: properties: annotations: additionalProperties: type: string description: Annotations for the router, e.g. for ingress class or gateway type: object eppConfig: description: EPPConfig is the configuration for the endpoint picker extension. This is field is currently only supported for standalone inference platform only on NIMService. properties: config: description: |- Config allows specifying EPP EndpointPickerConfig directly as a structured object. The operator will marshal this to YAML and create a ConfigMap automatically. Mutually exclusive with ConfigMapRef. One of ConfigMapRef or Config must be specified (no default configuration). Uses the upstream type from github.com/kubernetes-sigs/gateway-api-inference-extension properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string data: description: Data configures the DataLayer. It is required if the new DataLayer is enabled. properties: sources: description: Sources is the list of sources to define to the DataLayer items: description: DataLayerSource contains the configuration of a DataSource of the DataLayer feature properties: extractors: description: |- Extractors specifies the list of Plugin instances to be associated with this Source. The entries are references to the names of entries of the Plugins defined in the configuration's Plugins section items: description: DataLayerExtractor contains the configuration of an Extractor of the DataLayer feature properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Extractor. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - pluginRef type: object type: array pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Source. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - extractors - pluginRef type: object type: array required: - sources type: object featureGates: description: |- FeatureGates is a set of flags that enable various experimental features with the EPP. If omitted non of these experimental features will be enabled. items: type: string type: array kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string plugins: description: Plugins is the list of plugins that will be instantiated. items: description: |- PluginSpec contains the information that describes a plugin that will be instantiated. properties: name: description: |- Name provides a name for plugin entries to reference. If omitted, the value of the Plugin's Type field will be used. type: string parameters: description: |- Parameters are the set of parameters to be passed to the plugin's factory function. The factory function is responsible to parse the parameters. format: byte type: string type: description: Type specifies the plugin type to be instantiated. type: string required: - type type: object type: array saturationDetector: description: |- SaturationDetector when present specifies the configuration of the Saturation detector. If not present, default values are used. properties: kvCacheUtilThreshold: description: |- KVCacheUtilThreshold defines the KV cache utilization (0.0 to 1.0) above which a pod is considered to have insufficient capacity. type: number metricsStalenessThreshold: description: |- MetricsStalenessThreshold defines how old a pod's metrics can be. If a pod's metrics are older than this, it might be excluded from "good capacity" considerations or treated as having no capacity for safety. type: string queueDepthThreshold: description: |- QueueDepthThreshold defines the backend waiting queue size above which a pod is considered to have insufficient capacity for new requests. type: integer type: object schedulingProfiles: description: |- SchedulingProfiles is the list of named SchedulingProfiles that will be created. items: description: |- SchedulingProfile contains the information to create a SchedulingProfile entry to be used by the scheduler. properties: name: description: Name specifies the name of this SchedulingProfile type: string plugins: description: |- Plugins is the list of plugins for this SchedulingProfile. They are assigned to the appropriate "slots" based on their type. items: description: |- SchedulingPlugin describes a plugin that will be associated with a SchedulingProfile entry. properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this SchedulingProfile. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string weight: description: Weight is the weight fo be used if this plugin is a Scorer. type: integer required: - pluginRef type: object type: array required: - name - plugins type: object type: array required: - plugins - schedulingProfiles type: object x-kubernetes-preserve-unknown-fields: true configMapRef: description: |- ConfigMapRef references a user-provided ConfigMap containing EPP configuration. The ConfigMap should contain EndpointPickerConfig YAML. Mutually exclusive with Config. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic containerSpec: description: ContainerSpec is the specification for the EPP container. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object livenessProbe: description: LivenessProbe is the liveness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object ports: description: Ports is the list of ports to expose for the EPP container. items: description: ContainerPort represents a network port in a single container. properties: containerPort: description: |- Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. format: int32 type: integer hostIP: description: What host IP to bind the external port to. type: string hostPort: description: |- Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. format: int32 type: integer name: description: |- If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. type: string protocol: default: TCP description: |- Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". type: string required: - containerPort type: object type: array readinessProbe: description: ReadinessProbe is the readiness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object startupProbe: description: StartupProbe is the startup probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object required: - containerSpec type: object x-kubernetes-validations: - message: specify either configMapRef or config, not both rule: '!(has(self.configMapRef) && has(self.config))' gateway: description: Gateway is the gateway to use for the created HTTPRoute. properties: backendRef: description: BackendRef is a reference to a backend to forward matched requests to. properties: group: default: "" description: |- Group is the group of the referent. For example, "gateway.networking.k8s.io". When unspecified or empty string, core API group is inferred. maxLength: 253 pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ type: string kind: default: Service description: |- Kind is the Kubernetes resource kind of the referent. For example "Service". Defaults to "Service" when not specified. ExternalName services can refer to CNAME DNS records that may live outside of the cluster and as such are difficult to reason about in terms of conformance. They also may not be safe to forward to (see CVE-2021-25740 for more information). Implementations SHOULD NOT support ExternalName Services. Support: Core (Services with a type other than ExternalName) Support: Implementation-specific (Services with type ExternalName) maxLength: 63 minLength: 1 pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$ type: string name: description: Name is the name of the referent. maxLength: 253 minLength: 1 type: string namespace: description: |- Namespace is the namespace of the backend. When unspecified, the local namespace is inferred. Note that when a namespace different than the local namespace is specified, a ReferenceGrant object is required in the referent namespace to allow that namespace's owner to accept the reference. See the ReferenceGrant documentation for details. Support: Core maxLength: 63 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ type: string port: description: |- Port specifies the destination port number to use for this resource. Port is required when the referent is a Kubernetes Service. In this case, the port number is the service port number, not the target port. For other resources, destination port might be derived from the referent resource or this field. format: int32 maximum: 65535 minimum: 1 type: integer weight: default: 1 description: |- Weight specifies the proportion of requests forwarded to the referenced backend. This is computed as weight/(sum of all weights in this BackendRefs list). For non-zero values, there may be some epsilon from the exact proportion defined here depending on the precision an implementation supports. Weight is not a percentage and the sum of weights does not need to equal 100. If only one backend is specified and it has a weight greater than 0, 100% of the traffic is forwarded to that backend. If weight is set to 0, no traffic should be forwarded for this entry. If unspecified, weight defaults to 1. Support for this field varies based on the context where used. format: int32 maximum: 1000000 minimum: 0 type: integer required: - name type: object x-kubernetes-validations: - message: Must have port for Service reference rule: '(size(self.group) == 0 && self.kind == ''Service'') ? has(self.port) : true' grpcRoutesEnabled: default: false description: GRPCRoutesEnabled is a flag to enable GRPCRoutes for the created gateway. type: boolean httpRoutesEnabled: default: true description: HTTPRoutesEnabled is a flag to enable HTTPRoutes for the created gateway. type: boolean name: description: Name of the gateway minLength: 1 type: string namespace: description: Namespace of the gateway minLength: 1 type: string required: - name - namespace type: object hostDomainName: description: |- HostDomainName is the domain name of the hostname matched by the router. The hostname is constructed as "..", where the a subdomain of the matched hostname. eg. example.com for "..example.com" maxLength: 63 minLength: 1 pattern: ^(([a-z0-9][a-z0-9\-]*[a-z0-9])|[a-z0-9]+\.)*([a-z]+|xn\-\-[a-z0-9]+)\.?$ type: string ingress: description: Ingress is the ingress controller to use for the created ingress. properties: ingressClass: description: IngressClass is the ingress class to use for the created ingress. minLength: 1 type: string tlsSecretName: description: TLSSecretName is the name of the secret containing the TLS certificate and key. type: string required: - ingressClass type: object type: object x-kubernetes-validations: - message: 'unsupported field: spec.expose.router.gateway.grpcRoutesEnabled' rule: '!(has(self.gateway) && self.gateway.grpcRoutesEnabled)' - message: ingress and gateway cannot be specified together rule: '!(has(self.gateway) && has(self.ingress))' service: description: Service defines attributes to create a service. properties: annotations: additionalProperties: type: string type: object grpcPort: description: |- GRPCPort is the GRPC serving port Note: This port is only applicable for NIMs that runs a Triton GRPC Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer metricsPort: description: |- MetricsPort is the port for metrics Note: This port is only applicable for NIMs that runs a separate metrics endpoint on Triton Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer name: description: Override the default service name type: string port: default: 8000 description: 'Port is the main api serving port (default: 8000)' format: int32 maximum: 65535 minimum: 1 type: integer type: description: Service Type string describes ingress methods for a service type: string type: object type: object x-kubernetes-validations: - message: 'unsupported field: spec.expose.service.grpcPort' rule: '!(has(self.service.grpcPort))' - message: 'unsupported field: spec.expose.service.metricsPort' rule: '!(has(self.service.metricsPort))' groupID: format: int64 type: integer image: description: Image defines image attributes. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object labels: additionalProperties: type: string type: object metrics: description: Metrics defines attributes to setup metrics collection. properties: enabled: type: boolean serviceMonitor: description: for use with the Prometheus Operator and the primary service object properties: additionalLabels: additionalProperties: type: string type: object annotations: additionalProperties: type: string type: object interval: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string scrapeTimeout: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string type: object type: object nimEndpoint: properties: apiKeyKey: default: NIM_ENDPOINT_API_KEY description: The key in the secret that contains the API key for accessing the base URL endpoint. Defaults to `NIM_ENDPOINT_API_KEY` type: string apiKeySecret: description: |- The name of the secret that contains the API key for accessing the base URL endpoint. This is needed if the base URL is for a NIM proxy. When using NVIDIA's hosted NIM proxy `https://integrate.api.nvidia.com/v1` as the base URL, the API key can be retrieved from https://build.nvidia.com/explore/discover type: string baseURL: description: |- The base URL for the NIM service. This can either be the endpoint for a single NIM or a NIM proxy. A NIM proxy endpoint is needed if you need to run guardrail for serving multiple NIMs. format: uri minLength: 1 pattern: ^https?:\/\/[^\s]+\/v1\/?$ type: string required: - baseURL type: object nodeSelector: additionalProperties: type: string type: object otel: description: OpenTelemetry Settings properties: disableLogging: description: DisableLogging indicates whether Python logging auto-instrumentation should be disabled. type: boolean enabled: description: Enabled indicates if opentelemetry collector and tracing are enabled type: boolean excludedUrls: default: - health description: ExcludedUrls defines URLs to be excluded from tracing. items: type: string type: array exporterConfig: description: ExporterConfig defines configuration for different OTel exporters properties: logsExporter: default: otlp description: 'LogsExporter sets the logs exporter: (otlp, console, none).' enum: - otlp - console - none type: string metricsExporter: default: otlp description: 'MetricsExporter sets the metrics exporter: (otlp, console, none).' enum: - otlp - console - none type: string tracesExporter: default: otlp description: 'TracesExporter sets the traces exporter: (otlp, console, none).' enum: - otlp - console - none type: string type: object exporterOtlpEndpoint: description: ExporterOtlpEndpoint is the OTLP collector endpoint. type: string logLevel: default: INFO description: LogLevel defines the log level (e.g., INFO, DEBUG). enum: - INFO - DEBUG type: string type: object podAffinity: description: 'Deprecated: Use Affinity instead.' properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object replicas: format: int32 minimum: 1 type: integer resources: description: ResourceRequirements describes the compute resource requirements. properties: claims: description: |- Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. This field depends on the DynamicResourceAllocation feature gate. This field is immutable. It can only be set for containers. items: description: ResourceClaim references one entry in PodSpec.ResourceClaims. properties: name: description: |- Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. type: string request: description: |- Request is the name chosen for a request in the referenced claim. If empty, everything from the claim is made available, otherwise only the result of this request. type: string required: - name type: object type: array x-kubernetes-list-map-keys: - name x-kubernetes-list-type: map limits: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object runtimeClass: type: string scale: description: Autoscaling defines attributes to automatically scale the service based on metrics. properties: annotations: additionalProperties: type: string type: object enabled: type: boolean hpa: description: HorizontalPodAutoscalerSpec defines the parameters required to setup HPA. properties: behavior: description: |- HorizontalPodAutoscalerBehavior configures the scaling behavior of the target in both Up and Down directions (scaleUp and scaleDown fields respectively). properties: scaleDown: description: |- scaleDown is scaling policy for scaling Down. If not set, the default value is to allow to scale down to minReplicas pods, with a 300 second stabilization window (i.e., the highest recommendation for the last 300sec is used). properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object scaleUp: description: |- scaleUp is scaling policy for scaling Up. If not set, the default value is the higher of: * increase no more than 4 pods per 60 seconds * double the number of pods per 60 seconds No stabilization is used. properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object type: object maxReplicas: format: int32 type: integer metrics: items: description: |- MetricSpec specifies how to scale based on a single metric (only `type` and one other matching field should be set at once). properties: containerResource: description: |- containerResource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing a single container in each pod of the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: container: description: container is the name of the container in the pods of the scaling target type: string name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - container - name - target type: object external: description: |- external refers to a global metric that is not associated with any Kubernetes object. It allows autoscaling based on information coming from components running outside of cluster (for example length of queue in cloud messaging service, or QPS from loadbalancer running outside of cluster). properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object object: description: |- object refers to a metric describing a single kubernetes object (for example, hits-per-second on an Ingress object). properties: describedObject: description: describedObject specifies the descriptions of a object,such as kind,name apiVersion properties: apiVersion: description: apiVersion is the API version of the referent type: string kind: description: 'kind is the kind of the referent; More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'name is the name of the referent; More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' type: string required: - kind - name type: object metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - describedObject - metric - target type: object pods: description: |- pods refers to a metric describing each pod in the current scale target (for example, transactions-processed-per-second). The values will be averaged together before being compared to the target value. properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object resource: description: |- resource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing each pod in the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - name - target type: object type: description: |- type is the type of metric source. It should be one of "ContainerResource", "External", "Object", "Pods" or "Resource", each mapping to a matching field in the object. type: string required: - type type: object type: array minReplicas: default: 1 format: int32 minimum: 1 type: integer required: - maxReplicas type: object type: object tolerations: items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array userID: format: int64 type: integer required: - image type: object x-kubernetes-validations: - message: .spec.expose.ingress is deprecated, and will be removed in a future release. If .spec.expose.ingress is set, please do not set .spec.expose.router.ingress. rule: '!(has(self.expose.ingress) && has(self.expose.ingress.enabled) && self.expose.ingress.enabled && has(self.expose.router) && has(self.expose.router.ingress))' - message: spec.replicas cannot be set when spec.scale.enabled is true rule: '!(has(self.scale) && has(self.scale.enabled) && self.scale.enabled && has(self.replicas))' status: description: NemoGuardrailStatus defines the observed state of NemoGuardrail. properties: availableReplicas: format: int32 type: integer conditions: items: description: Condition contains details for one aspect of the current state of this API Resource. properties: lastTransitionTime: description: |- lastTransitionTime is the last time the condition transitioned from one status to another. This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable. format: date-time type: string message: description: |- message is a human readable message indicating details about the transition. This may be an empty string. maxLength: 32768 type: string observedGeneration: description: |- observedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date with respect to the current state of the instance. format: int64 minimum: 0 type: integer reason: description: |- reason contains a programmatic identifier indicating the reason for the condition's last transition. Producers of specific condition types may define expected values and meanings for this field, and whether the values are considered a guaranteed API. The value should be a CamelCase string. This field may not be empty. maxLength: 1024 minLength: 1 pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$ type: string status: description: status of the condition, one of True, False, Unknown. enum: - "True" - "False" - Unknown type: string type: description: type of condition in CamelCase or in foo.example.com/CamelCase. maxLength: 316 pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$ type: string required: - lastTransitionTime - message - reason - status - type type: object type: array state: type: string type: object type: object served: true storage: true subresources: status: {} --- # Source: k8s-nim-operator/crds/apps.nvidia.com_nimbuilds.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.0 name: nimbuilds.apps.nvidia.com spec: group: apps.nvidia.com names: kind: NIMBuild listKind: NIMBuildList plural: nimbuilds singular: nimbuild scope: Namespaced versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - format: date-time jsonPath: .metadata.creationTimestamp name: Age type: date name: v1alpha1 schema: openAPIV3Schema: description: NIMBuild is the Schema for the nimcaches API. properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string metadata: type: object spec: description: NIMBuildSpec to build optimized trtllm engines with given model config and weights. properties: annotations: additionalProperties: type: string type: object env: items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image defines image attributes. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object labels: additionalProperties: type: string type: object modelName: description: ModelName is the name given to the locally built engine. type: string nimCache: description: NIMCache is Reference to the model weights from NIMCache properties: name: type: string profile: type: string required: - name type: object nodeSelector: additionalProperties: type: string description: NodeSelector is the node selector labels to schedule the caching job. type: object resources: description: Resources is the resource requirements for the NIMBuild pod. properties: limits: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object tolerations: description: Tolerations for running the job to cache the NIM model items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array required: - image - nimCache type: object x-kubernetes-validations: - message: spec is immutable rule: self == oldSelf status: description: NIMBuildStatus defines the observed state of NIMBuild. properties: conditions: items: description: Condition contains details for one aspect of the current state of this API Resource. properties: lastTransitionTime: description: |- lastTransitionTime is the last time the condition transitioned from one status to another. This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable. format: date-time type: string message: description: |- message is a human readable message indicating details about the transition. This may be an empty string. maxLength: 32768 type: string observedGeneration: description: |- observedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date with respect to the current state of the instance. format: int64 minimum: 0 type: integer reason: description: |- reason contains a programmatic identifier indicating the reason for the condition's last transition. Producers of specific condition types may define expected values and meanings for this field, and whether the values are considered a guaranteed API. The value should be a CamelCase string. This field may not be empty. maxLength: 1024 minLength: 1 pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$ type: string status: description: status of the condition, one of True, False, Unknown. enum: - "True" - "False" - Unknown type: string type: description: type of condition in CamelCase or in foo.example.com/CamelCase. maxLength: 316 pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$ type: string required: - lastTransitionTime - message - reason - status - type type: object type: array inputProfile: description: NIMProfile defines the profiles that were cached. properties: config: additionalProperties: type: string type: object model: type: string name: type: string release: type: string type: object outputProfile: description: NIMProfile defines the profiles that were cached. properties: config: additionalProperties: type: string type: object model: type: string name: type: string release: type: string type: object state: type: string type: object type: object served: true storage: true subresources: status: {} --- # Source: k8s-nim-operator/crds/apps.nvidia.com_nimcaches.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.0 name: nimcaches.apps.nvidia.com spec: group: apps.nvidia.com names: kind: NIMCache listKind: NIMCacheList plural: nimcaches singular: nimcache scope: Namespaced versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - jsonPath: .status.pvc name: PVC type: string - format: date-time jsonPath: .metadata.creationTimestamp name: Age type: date name: v1alpha1 schema: openAPIV3Schema: description: NIMCache is the Schema for the nimcaches API. properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string metadata: type: object spec: description: NIMCacheSpec defines the desired state of NIMCache. properties: certConfig: description: |- CertConfig is the name of the ConfigMap containing the custom certificates. for secure communication. Deprecated: use `Proxy` instead to configure custom certificates for using proxy. properties: mountPath: description: MountPath is the path where the certificates should be mounted in the container. type: string name: description: Name of the ConfigMap containing the certificate data. type: string required: - mountPath - name type: object env: description: Env are the additional custom environment variabes for the caching job items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array groupID: description: GroupID is the group ID for the caching job format: int64 type: integer initContainers: items: description: NIMContainerSpec defines the specification for a container within a NIM workload. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object type: array nodeSelector: additionalProperties: type: string description: NodeSelector is the node selector labels to schedule the caching job. type: object proxy: description: ProxySpec defines the proxy configuration for NIMService. properties: certConfigMap: type: string httpProxy: type: string httpsProxy: type: string noProxy: type: string type: object resources: description: Resources defines the minimum resources required for the caching job to run(cpu, memory, gpu). properties: cpu: anyOf: - type: integer - type: string description: CPU indicates the minimum number of CPUs to use while caching NIM pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true memory: anyOf: - type: integer - type: string description: |- Memory indicates the minimum amount of memory to use while caching NIM Valid values are numbers followed by one of the suffixes Ki, Mi, Gi, or Ti (e.g. "4Gi", "4096Mi"). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object runtimeClassName: description: RuntimeClassName is the runtimeclass for the caching job type: string source: description: Source is the NIM model source to cache properties: dataStore: description: DataStore represents models stored in NVIDIA NeMo DataStore service properties: authSecret: description: AuthSecret is the name of the secret containing the "HF_TOKEN" token minLength: 1 type: string datasetName: description: DatasetName is the name of the dataset type: string endpoint: description: Endpoint is the HuggingFace endpoint from NeMo DataStore pattern: ^https?://.*/v1/hf/?$ type: string modelName: description: ModelName is the name of the model type: string modelPuller: description: ModelPuller is the containerized huggingface-cli image to pull the data minLength: 1 type: string namespace: default: default description: Namespace is the namespace within NeMo DataStore type: string pullSecret: description: PullSecret is the name of the image pull secret for the modelPuller image minLength: 1 type: string revision: description: Revision is the revision of the object to be cached. This is either a commit hash, branch name or tag. minLength: 1 type: string required: - authSecret - endpoint - modelPuller - namespace - pullSecret type: object x-kubernetes-validations: - message: Exactly one of modelName or datasetName must be defined rule: '(has(self.modelName) ? 1 : 0) + (has(self.datasetName) ? 1 : 0) == 1' hf: description: HuggingFaceHub represents models stored in HuggingFace Hub properties: authSecret: description: AuthSecret is the name of the secret containing the "HF_TOKEN" token minLength: 1 type: string datasetName: description: DatasetName is the name of the dataset type: string endpoint: description: Endpoint is the HuggingFace endpoint pattern: ^https?://.*$ type: string modelName: description: ModelName is the name of the model type: string modelPuller: description: ModelPuller is the containerized huggingface-cli image to pull the data minLength: 1 type: string namespace: description: Namespace is the namespace within the HuggingFace Hub minLength: 1 type: string pullSecret: description: PullSecret is the name of the image pull secret for the modelPuller image minLength: 1 type: string revision: description: Revision is the revision of the object to be cached. This is either a commit hash, branch name or tag. minLength: 1 type: string required: - authSecret - endpoint - modelPuller - namespace - pullSecret type: object x-kubernetes-validations: - message: Exactly one of modelName or datasetName must be defined rule: '(has(self.modelName) ? 1 : 0) + (has(self.datasetName) ? 1 : 0) == 1' ngc: description: NGCSource represents models stored in NGC properties: authSecret: description: The name of an existing pull secret containing the NGC_API_KEY type: string model: description: Model spec for caching properties: buildable: description: Buildable indicates generic model profiles that can be optimized with an NVIDIA engine for any GPUs type: boolean engine: description: Engine is the backend engine (tensorrt_llm, vllm) type: string gpus: description: GPU is the spec for matching GPUs for caching optimized models items: description: GPUSpec is the spec required to cache models for selected gpu type. properties: ids: description: IDs are the device-ids for a specific GPU SKU items: type: string type: array product: description: Product is the GPU product string (h100, a100, l40s) type: string type: object type: array lora: description: Lora indicates a finetuned model with LoRa adapters type: boolean precision: description: Precision is the precision for model quantization type: string profiles: description: Profiles are the specific model profiles to cache. When these are provided, rest of the model parameters for profile selection are ignored items: type: string type: array qosProfile: description: QoSProfile is the supported QoS profile types for the models (throughput, latency) type: string tensorParallelism: description: TensorParallelism is the minimum GPUs required for the model computations type: string type: object modelEndpoint: description: ModelEndpoint is the endpoint for the model to be cached for Universal NIM type: string modelPuller: description: ModelPuller is the container image that can pull the model type: string x-kubernetes-validations: - message: modelPuller is an immutable field. Please create a new NIMCache resource instead when you want to change this container. rule: self == oldSelf pullSecret: description: PullSecret to pull the model puller image type: string required: - authSecret - modelPuller type: object x-kubernetes-validations: - message: Only one of 'model' or 'modelEndpoint' can be specified rule: '!(has(self.model) && has(self.modelEndpoint))' type: object x-kubernetes-validations: - message: Exactly one of ngc, dataStore, or hf must be defined rule: '(has(self.ngc) ? 1 : 0) + (has(self.dataStore) ? 1 : 0) + (has(self.hf) ? 1 : 0) == 1' storage: description: Storage is the target storage for caching NIM model properties: hostPath: description: |- HostPath is the host path volume for caching NIM Deprecated: use PVC instead. type: string pvc: description: PersistentVolumeClaim is the pvc volume used for caching NIM properties: annotations: additionalProperties: type: string description: Annotations for the PVC type: object create: description: |- Create specifies whether to create a new PersistentVolumeClaim (PVC). If set to false, an existing PVC must be referenced via the `Name` field. type: boolean name: description: Name of the PVC to use. Required if `Create` is false (i.e., using an existing PVC). type: string size: description: Size of the NIM cache in Gi, used during PVC creation type: string storageClass: description: |- StorageClass to be used for PVC creation. Leave it as empty if the PVC is already created or a default storage class is set in the cluster. type: string subPath: description: SubPath is the path inside the PVC that should be mounted type: string volumeAccessMode: description: VolumeAccessMode is the volume access mode of the PVC type: string type: object type: object tolerations: description: Tolerations for running the job to cache the NIM model items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array userID: description: UserID is the user ID for the caching job format: int64 type: integer required: - source - storage type: object status: description: NIMCacheStatus defines the observed state of NIMCache. properties: conditions: items: description: Condition contains details for one aspect of the current state of this API Resource. properties: lastTransitionTime: description: |- lastTransitionTime is the last time the condition transitioned from one status to another. This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable. format: date-time type: string message: description: |- message is a human readable message indicating details about the transition. This may be an empty string. maxLength: 32768 type: string observedGeneration: description: |- observedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date with respect to the current state of the instance. format: int64 minimum: 0 type: integer reason: description: |- reason contains a programmatic identifier indicating the reason for the condition's last transition. Producers of specific condition types may define expected values and meanings for this field, and whether the values are considered a guaranteed API. The value should be a CamelCase string. This field may not be empty. maxLength: 1024 minLength: 1 pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$ type: string status: description: status of the condition, one of True, False, Unknown. enum: - "True" - "False" - Unknown type: string type: description: type of condition in CamelCase or in foo.example.com/CamelCase. maxLength: 316 pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$ type: string required: - lastTransitionTime - message - reason - status - type type: object type: array profiles: items: description: NIMProfile defines the profiles that were cached. properties: config: additionalProperties: type: string type: object model: type: string name: type: string release: type: string type: object type: array pvc: type: string state: type: string type: object type: object served: true storage: true subresources: status: {} --- # Source: k8s-nim-operator/crds/apps.nvidia.com_nimpipelines.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.0 name: nimpipelines.apps.nvidia.com spec: group: apps.nvidia.com names: kind: NIMPipeline listKind: NIMPipelineList plural: nimpipelines singular: nimpipeline scope: Namespaced versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - format: date-time jsonPath: .metadata.creationTimestamp name: Age type: date name: v1alpha1 schema: openAPIV3Schema: description: NIMPipeline is the Schema for the nimpipelines API. properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string metadata: type: object spec: description: NIMPipelineSpec defines the desired state of NIMPipeline. properties: services: description: NIMService configures attributes to deploy a NIM service as part of the pipeline items: description: NIMServicePipelineSpec defines the desired state of NIMService as part of the NIMPipeline. properties: dependencies: items: description: ServiceDependency defines service dependencies. properties: envName: description: EnvName is the dependent service endpoint environment variable name type: string envValue: description: EnvValue is the dependent service endpoint environment variable value type: string name: description: Name is the dependent service name type: string port: description: Port is the dependent service port format: int32 type: integer required: - name - port type: object type: array enabled: type: boolean name: type: string spec: description: NIMServiceSpec defines the desired state of NIMService. properties: affinity: description: Affinity is a group of affinity scheduling rules. properties: nodeAffinity: description: Describes node affinity scheduling rules for the pod. properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. items: description: |- An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). properties: preference: description: A node selector term, associated with the corresponding weight. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic weight: description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. format: int32 type: integer required: - preference - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. properties: nodeSelectorTerms: description: Required. A list of node selector terms. The terms are ORed. items: description: |- A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic type: array x-kubernetes-list-type: atomic required: - nodeSelectorTerms type: object x-kubernetes-map-type: atomic type: object podAffinity: description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object podAntiAffinity: description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and subtracting "weight" from the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object type: object annotations: additionalProperties: type: string type: object args: items: type: string type: array authSecret: description: The name of an existing pull secret containing the NGC_API_KEY type: string command: items: type: string type: array draResources: description: DRAResources is the list of DRA resource claims to be used for the NIMService deployment or leader worker set. items: description: |- DRAResource references exactly one ResourceClaim, either directly or by naming a ResourceClaimTemplate which is then turned into a ResourceClaim. When creating the NIMService pods, it adds a name (`DNS_LABEL` format) to it that uniquely identifies the DRA resource. properties: claimCreationSpec: description: |- ClaimCreationSpec is the spec to auto-generate a DRA resource claim template. Only one of ClaimCreationSpec, ResourceClaimName or ResourceClaimTemplateName must be specified. properties: devices: items: properties: attributeSelectors: description: AttributeSelectors defines the criteria which must be satisfied by the device attributes of a device. items: description: DRADeviceAttributeSelector defines the selector expression for a DRA device attribute. properties: key: description: |- Key is the name of the device attribute. This is either a qualified name or a simple name. If it is a simple name, then it is assumed to be prefixed with the DRA driver name. Eg: "gpu.nvidia.com/productName" is equivalent to "productName" if the driver name is "gpu.nvidia.com". Otherwise they're treated as 2 different attributes. maxLength: 64 type: string op: default: Equal description: |- Op is the operator to use for comparing the device attribute value. Supported operators are: * Equal: The device attribute value must be equal to the value specified in the selector. * NotEqual: The device attribute value must not be equal to the value specified in the selector. * GreaterThan: The device attribute value must be greater than the value specified in the selector. * GreaterThanOrEqual: The device attribute value must be greater than or equal to the value specified in the selector. * LessThan: The device attribute value must be less than the value specified in the selector. * LessThanOrEqual: The device attribute value must be less than or equal to the value specified in the selector. enum: - Equal - NotEqual - GreaterThan - GreaterThanOrEqual - LessThan - LessThanOrEqual type: string value: description: Value is the value to compare against the device attribute. properties: boolValue: description: BoolValue is a true/false value. type: boolean intValue: description: IntValue is a number. format: int32 type: integer stringValue: description: StringValue is a string value. maxLength: 64 type: string versionValue: description: VersionValue is a semantic version according to semver.org spec 2.0.0. maxLength: 64 type: string type: object required: - key - op type: object type: array capacitySelectors: description: CapacitySelectors defines the criteria which must be satisfied by the device capacity of a device. items: description: DRAResourceQuantitySelector defines the selector expression for a DRA device capacity. properties: key: description: |- Key is the name of the resource. This is either a qualified name or a simple name. If it is a simple name, then it is assumed to be prefixed with the DRA driver name. Eg: "gpu.nvidia.com/memory" is equivalent to "memory" if the driver name is "gpu.nvidia.com". Otherwise they're treated as 2 different attributes. maxLength: 64 type: string op: default: Equal description: |- Op is the operator to use for comparing against the device capacity. Supported operators are: * Equal: The resource quantity value must be equal to the value specified in the selector. * NotEqual: The resource quantity value must not be equal to the value specified in the selector. * GreaterThan: The resource quantity value must be greater than the value specified in the selector. * GreaterThanOrEqual: The resource quantity value must be greater than or equal to the value specified in the selector. * LessThan: The resource quantity value must be less than the value specified in the selector. * LessThanOrEqual: The resource quantity value must be less than or equal to the value specified in the selector. enum: - Equal - NotEqual - GreaterThan - GreaterThanOrEqual - LessThan - LessThanOrEqual type: string value: anyOf: - type: integer - type: string description: Value is the resource quantity to compare against. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - key - op - value type: object type: array celExpressions: description: CELExpressions is a list of CEL expressions that must be satisfied by the DRA device. items: type: string type: array count: default: 1 description: Count is the number of devices to request. format: int32 type: integer deviceClassName: default: gpu.nvidia.com description: DeviceClassName references a specific DeviceClass to inherit configuration and selectors from. type: string driverName: default: gpu.nvidia.com description: |- DriverName is the name of the DRA driver providing the capacity information. Must be a DNS subdomain. maxLength: 253 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)* type: string name: description: |- Name is the name of the device request to use in the generated claim spec. Must be a valid DNS_LABEL. maxLength: 253 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)* type: string required: - count - deviceClassName - name type: object x-kubernetes-validations: - message: celExpressions must not be set if attributeSelectors or capacitySelectors are set rule: (has(self.celExpressions) && !(has(self.attributeSelectors) || has(self.capacitySelectors))) || !has(self.celExpressions) type: array generateName: description: GenerateName is an optional name prefix to use for generating the resource claim template. maxLength: 16 minLength: 1 type: string required: - devices type: object requests: description: |- Requests is the list of requests in the referenced DRA resource claim. to be made available to the model container of the NIMService pods. If empty, everything from the claim is made available, otherwise only the result of this subset of requests. items: minLength: 1 type: string type: array resourceClaimName: description: |- ResourceClaimName is the name of a DRA resource claim object in the same namespace as the NIMService. Exactly one of ResourceClaimName and ResourceClaimTemplateName must be set. maxLength: 253 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)* type: string resourceClaimTemplateName: description: |- ResourceClaimTemplateName is the name of a DRA resource claim template object in the same namespace as the pods for this NIMService. The template will be used to create a new DRA resource claim, which will be bound to the pods created for this NIMService. Exactly one of ResourceClaimName and ResourceClaimTemplateName must be set. maxLength: 253 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)* type: string type: object x-kubernetes-validations: - message: exactly one of spec.resourceClaimName, spec.resourceClaimTemplateName, or spec.claimCreationSpec must be set. rule: '(has(self.resourceClaimName) ? 1 : 0) + (has(self.resourceClaimTemplateName) ? 1 : 0) + (has(self.claimCreationSpec) ? 1 : 0) == 1' type: array env: items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array expose: description: Expose defines attributes to expose the service. properties: ingress: description: 'Deprecated: Use .spec.expose.router instead.' properties: annotations: additionalProperties: type: string type: object enabled: description: ingress, or virtualService - not both type: boolean spec: description: IngressSpec describes the Ingress the user wishes to exist. properties: defaultBackend: description: |- defaultBackend is the backend that should handle requests that don't match any rule. If Rules are not specified, DefaultBackend must be specified. If DefaultBackend is not set, the handling of requests that do not match any of the rules will be up to the Ingress controller. properties: resource: description: |- resource is an ObjectRef to another Kubernetes resource in the namespace of the Ingress object. If resource is specified, a service.Name and service.Port must not be specified. This is a mutually exclusive setting with "Service". properties: apiGroup: description: |- APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. type: string kind: description: Kind is the type of resource being referenced type: string name: description: Name is the name of resource being referenced type: string required: - kind - name type: object x-kubernetes-map-type: atomic service: description: |- service references a service as a backend. This is a mutually exclusive setting with "Resource". properties: name: description: |- name is the referenced service. The service must exist in the same namespace as the Ingress object. type: string port: description: |- port of the referenced service. A port name or port number is required for a IngressServiceBackend. properties: name: description: |- name is the name of the port on the Service. This is a mutually exclusive setting with "Number". type: string number: description: |- number is the numerical port number (e.g. 80) on the Service. This is a mutually exclusive setting with "Name". format: int32 type: integer type: object x-kubernetes-map-type: atomic required: - name type: object type: object ingressClassName: description: |- ingressClassName is the name of an IngressClass cluster resource. Ingress controller implementations use this field to know whether they should be serving this Ingress resource, by a transitive connection (controller -> IngressClass -> Ingress resource). Although the `kubernetes.io/ingress.class` annotation (simple constant name) was never formally defined, it was widely supported by Ingress controllers to create a direct binding between Ingress controller and Ingress resources. Newly created Ingress resources should prefer using the field. However, even though the annotation is officially deprecated, for backwards compatibility reasons, ingress controllers should still honor that annotation if present. type: string rules: description: |- rules is a list of host rules used to configure the Ingress. If unspecified, or no rule matches, all traffic is sent to the default backend. items: description: |- IngressRule represents the rules mapping the paths under a specified host to the related backend services. Incoming requests are first evaluated for a host match, then routed to the backend associated with the matching IngressRuleValue. properties: host: description: "host is the fully qualified domain name of a network host, as defined by RFC 3986.\nNote the following deviations from the \"host\" part of the\nURI as defined in RFC 3986:\n1. IPs are not allowed. Currently an IngressRuleValue can only apply to\n the IP in the Spec of the parent Ingress.\n2. The `:` delimiter is not respected because ports are not allowed.\n\t Currently the port of an Ingress is implicitly :80 for http and\n\t :443 for https.\nBoth these may change in the future.\nIncoming requests are matched against the host before the\nIngressRuleValue. If the host is unspecified, the Ingress routes all\ntraffic based on the specified IngressRuleValue.\n\nhost can be \"precise\" which is a domain name without the terminating dot of\na network host (e.g. \"foo.bar.com\") or \"wildcard\", which is a domain name\nprefixed with a single wildcard label (e.g. \"*.foo.com\").\nThe wildcard character '*' must appear by itself as the first DNS label and\nmatches only a single label. You cannot have a wildcard label by itself (e.g. Host == \"*\").\nRequests will be matched against the Host field in the following way:\n1. If host is precise, the request matches this rule if the http host header is equal to Host.\n2. If host is a wildcard, then the request matches this rule if the http host header\nis to equal to the suffix (removing the first label) of the wildcard rule." type: string http: description: |- HTTPIngressRuleValue is a list of http selectors pointing to backends. In the example: http:///? -> backend where where parts of the url correspond to RFC 3986, this resource will be used to match against everything after the last '/' and before the first '?' or '#'. properties: paths: description: paths is a collection of paths that map requests to backends. items: description: |- HTTPIngressPath associates a path with a backend. Incoming urls matching the path are forwarded to the backend. properties: backend: description: |- backend defines the referenced service endpoint to which the traffic will be forwarded to. properties: resource: description: |- resource is an ObjectRef to another Kubernetes resource in the namespace of the Ingress object. If resource is specified, a service.Name and service.Port must not be specified. This is a mutually exclusive setting with "Service". properties: apiGroup: description: |- APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. type: string kind: description: Kind is the type of resource being referenced type: string name: description: Name is the name of resource being referenced type: string required: - kind - name type: object x-kubernetes-map-type: atomic service: description: |- service references a service as a backend. This is a mutually exclusive setting with "Resource". properties: name: description: |- name is the referenced service. The service must exist in the same namespace as the Ingress object. type: string port: description: |- port of the referenced service. A port name or port number is required for a IngressServiceBackend. properties: name: description: |- name is the name of the port on the Service. This is a mutually exclusive setting with "Number". type: string number: description: |- number is the numerical port number (e.g. 80) on the Service. This is a mutually exclusive setting with "Name". format: int32 type: integer type: object x-kubernetes-map-type: atomic required: - name type: object type: object path: description: |- path is matched against the path of an incoming request. Currently it can contain characters disallowed from the conventional "path" part of a URL as defined by RFC 3986. Paths must begin with a '/' and must be present when using PathType with value "Exact" or "Prefix". type: string pathType: description: |- pathType determines the interpretation of the path matching. PathType can be one of the following values: * Exact: Matches the URL path exactly. * Prefix: Matches based on a URL path prefix split by '/'. Matching is done on a path element by element basis. A path element refers is the list of labels in the path split by the '/' separator. A request is a match for path p if every p is an element-wise prefix of p of the request path. Note that if the last element of the path is a substring of the last element in request path, it is not a match (e.g. /foo/bar matches /foo/bar/baz, but does not match /foo/barbaz). * ImplementationSpecific: Interpretation of the Path matching is up to the IngressClass. Implementations can treat this as a separate PathType or treat it identically to Prefix or Exact path types. Implementations are required to support all path types. type: string required: - backend - pathType type: object type: array x-kubernetes-list-type: atomic required: - paths type: object type: object type: array x-kubernetes-list-type: atomic tls: description: |- tls represents the TLS configuration. Currently the Ingress only supports a single TLS port, 443. If multiple members of this list specify different hosts, they will be multiplexed on the same port according to the hostname specified through the SNI TLS extension, if the ingress controller fulfilling the ingress supports SNI. items: description: IngressTLS describes the transport layer security associated with an ingress. properties: hosts: description: |- hosts is a list of hosts included in the TLS certificate. The values in this list must match the name/s used in the tlsSecret. Defaults to the wildcard host setting for the loadbalancer controller fulfilling this Ingress, if left unspecified. items: type: string type: array x-kubernetes-list-type: atomic secretName: description: |- secretName is the name of the secret used to terminate TLS traffic on port 443. Field is left optional to allow TLS routing based on SNI hostname alone. If the SNI host in a listener conflicts with the "Host" header field used by an IngressRule, the SNI host is used for termination and value of the "Host" header is used for routing. type: string type: object type: array x-kubernetes-list-type: atomic type: object type: object router: properties: annotations: additionalProperties: type: string description: Annotations for the router, e.g. for ingress class or gateway type: object eppConfig: description: EPPConfig is the configuration for the endpoint picker extension. This is field is currently only supported for standalone inference platform only on NIMService. properties: config: description: |- Config allows specifying EPP EndpointPickerConfig directly as a structured object. The operator will marshal this to YAML and create a ConfigMap automatically. Mutually exclusive with ConfigMapRef. One of ConfigMapRef or Config must be specified (no default configuration). Uses the upstream type from github.com/kubernetes-sigs/gateway-api-inference-extension properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string data: description: Data configures the DataLayer. It is required if the new DataLayer is enabled. properties: sources: description: Sources is the list of sources to define to the DataLayer items: description: DataLayerSource contains the configuration of a DataSource of the DataLayer feature properties: extractors: description: |- Extractors specifies the list of Plugin instances to be associated with this Source. The entries are references to the names of entries of the Plugins defined in the configuration's Plugins section items: description: DataLayerExtractor contains the configuration of an Extractor of the DataLayer feature properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Extractor. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - pluginRef type: object type: array pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Source. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - extractors - pluginRef type: object type: array required: - sources type: object featureGates: description: |- FeatureGates is a set of flags that enable various experimental features with the EPP. If omitted non of these experimental features will be enabled. items: type: string type: array kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string plugins: description: Plugins is the list of plugins that will be instantiated. items: description: |- PluginSpec contains the information that describes a plugin that will be instantiated. properties: name: description: |- Name provides a name for plugin entries to reference. If omitted, the value of the Plugin's Type field will be used. type: string parameters: description: |- Parameters are the set of parameters to be passed to the plugin's factory function. The factory function is responsible to parse the parameters. format: byte type: string type: description: Type specifies the plugin type to be instantiated. type: string required: - type type: object type: array saturationDetector: description: |- SaturationDetector when present specifies the configuration of the Saturation detector. If not present, default values are used. properties: kvCacheUtilThreshold: description: |- KVCacheUtilThreshold defines the KV cache utilization (0.0 to 1.0) above which a pod is considered to have insufficient capacity. type: number metricsStalenessThreshold: description: |- MetricsStalenessThreshold defines how old a pod's metrics can be. If a pod's metrics are older than this, it might be excluded from "good capacity" considerations or treated as having no capacity for safety. type: string queueDepthThreshold: description: |- QueueDepthThreshold defines the backend waiting queue size above which a pod is considered to have insufficient capacity for new requests. type: integer type: object schedulingProfiles: description: |- SchedulingProfiles is the list of named SchedulingProfiles that will be created. items: description: |- SchedulingProfile contains the information to create a SchedulingProfile entry to be used by the scheduler. properties: name: description: Name specifies the name of this SchedulingProfile type: string plugins: description: |- Plugins is the list of plugins for this SchedulingProfile. They are assigned to the appropriate "slots" based on their type. items: description: |- SchedulingPlugin describes a plugin that will be associated with a SchedulingProfile entry. properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this SchedulingProfile. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string weight: description: Weight is the weight fo be used if this plugin is a Scorer. type: integer required: - pluginRef type: object type: array required: - name - plugins type: object type: array required: - plugins - schedulingProfiles type: object x-kubernetes-preserve-unknown-fields: true configMapRef: description: |- ConfigMapRef references a user-provided ConfigMap containing EPP configuration. The ConfigMap should contain EndpointPickerConfig YAML. Mutually exclusive with Config. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic containerSpec: description: ContainerSpec is the specification for the EPP container. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object livenessProbe: description: LivenessProbe is the liveness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object ports: description: Ports is the list of ports to expose for the EPP container. items: description: ContainerPort represents a network port in a single container. properties: containerPort: description: |- Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. format: int32 type: integer hostIP: description: What host IP to bind the external port to. type: string hostPort: description: |- Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. format: int32 type: integer name: description: |- If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. type: string protocol: default: TCP description: |- Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". type: string required: - containerPort type: object type: array readinessProbe: description: ReadinessProbe is the readiness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object startupProbe: description: StartupProbe is the startup probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object required: - containerSpec type: object x-kubernetes-validations: - message: specify either configMapRef or config, not both rule: '!(has(self.configMapRef) && has(self.config))' gateway: description: Gateway is the gateway to use for the created HTTPRoute. properties: backendRef: description: BackendRef is a reference to a backend to forward matched requests to. properties: group: default: "" description: |- Group is the group of the referent. For example, "gateway.networking.k8s.io". When unspecified or empty string, core API group is inferred. maxLength: 253 pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ type: string kind: default: Service description: |- Kind is the Kubernetes resource kind of the referent. For example "Service". Defaults to "Service" when not specified. ExternalName services can refer to CNAME DNS records that may live outside of the cluster and as such are difficult to reason about in terms of conformance. They also may not be safe to forward to (see CVE-2021-25740 for more information). Implementations SHOULD NOT support ExternalName Services. Support: Core (Services with a type other than ExternalName) Support: Implementation-specific (Services with type ExternalName) maxLength: 63 minLength: 1 pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$ type: string name: description: Name is the name of the referent. maxLength: 253 minLength: 1 type: string namespace: description: |- Namespace is the namespace of the backend. When unspecified, the local namespace is inferred. Note that when a namespace different than the local namespace is specified, a ReferenceGrant object is required in the referent namespace to allow that namespace's owner to accept the reference. See the ReferenceGrant documentation for details. Support: Core maxLength: 63 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ type: string port: description: |- Port specifies the destination port number to use for this resource. Port is required when the referent is a Kubernetes Service. In this case, the port number is the service port number, not the target port. For other resources, destination port might be derived from the referent resource or this field. format: int32 maximum: 65535 minimum: 1 type: integer weight: default: 1 description: |- Weight specifies the proportion of requests forwarded to the referenced backend. This is computed as weight/(sum of all weights in this BackendRefs list). For non-zero values, there may be some epsilon from the exact proportion defined here depending on the precision an implementation supports. Weight is not a percentage and the sum of weights does not need to equal 100. If only one backend is specified and it has a weight greater than 0, 100% of the traffic is forwarded to that backend. If weight is set to 0, no traffic should be forwarded for this entry. If unspecified, weight defaults to 1. Support for this field varies based on the context where used. format: int32 maximum: 1000000 minimum: 0 type: integer required: - name type: object x-kubernetes-validations: - message: Must have port for Service reference rule: '(size(self.group) == 0 && self.kind == ''Service'') ? has(self.port) : true' grpcRoutesEnabled: default: false description: GRPCRoutesEnabled is a flag to enable GRPCRoutes for the created gateway. type: boolean httpRoutesEnabled: default: true description: HTTPRoutesEnabled is a flag to enable HTTPRoutes for the created gateway. type: boolean name: description: Name of the gateway minLength: 1 type: string namespace: description: Namespace of the gateway minLength: 1 type: string required: - name - namespace type: object hostDomainName: description: |- HostDomainName is the domain name of the hostname matched by the router. The hostname is constructed as "..", where the a subdomain of the matched hostname. eg. example.com for "..example.com" maxLength: 63 minLength: 1 pattern: ^(([a-z0-9][a-z0-9\-]*[a-z0-9])|[a-z0-9]+\.)*([a-z]+|xn\-\-[a-z0-9]+)\.?$ type: string ingress: description: Ingress is the ingress controller to use for the created ingress. properties: ingressClass: description: IngressClass is the ingress class to use for the created ingress. minLength: 1 type: string tlsSecretName: description: TLSSecretName is the name of the secret containing the TLS certificate and key. type: string required: - ingressClass type: object type: object x-kubernetes-validations: - message: ingress and gateway cannot be specified together rule: '!(has(self.gateway) && has(self.ingress))' service: description: Service defines attributes to create a service. properties: annotations: additionalProperties: type: string type: object grpcPort: description: |- GRPCPort is the GRPC serving port Note: This port is only applicable for NIMs that runs a Triton GRPC Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer metricsPort: description: |- MetricsPort is the port for metrics Note: This port is only applicable for NIMs that runs a separate metrics endpoint on Triton Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer name: description: Override the default service name type: string port: default: 8000 description: 'Port is the main api serving port (default: 8000)' format: int32 maximum: 65535 minimum: 1 type: integer type: description: Service Type string describes ingress methods for a service type: string type: object type: object groupID: format: int64 type: integer image: description: Image defines image attributes. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object inferencePlatform: default: standalone description: |- InferencePlatform specifies the inference platform to use for this NIMService. Valid values are "standalone" (default) and "kserve". enum: - standalone - kserve type: string initContainers: items: description: NIMContainerSpec defines the specification for a container within a NIM workload. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object type: array labels: additionalProperties: type: string type: object livenessProbe: description: Probe defines attributes for startup/liveness/readiness probes. properties: enabled: type: boolean probe: description: |- Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object type: object metrics: description: Metrics defines attributes to setup metrics collection. properties: enabled: type: boolean serviceMonitor: description: for use with the Prometheus Operator and the primary service object properties: additionalLabels: additionalProperties: type: string type: object annotations: additionalProperties: type: string type: object interval: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string scrapeTimeout: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string type: object type: object multiNode: description: NimServiceMultiNodeConfig defines the configuration for multi-node NIMService. properties: backendType: default: lws description: BackendType specifies the backend type for the multi-node NIMService. Currently only LWS is supported. enum: - lws type: string computeDomain: description: |- ComputeDomain specifies the compute domain to use for a multi-node NIMService. properties: create: description: |- Create specifies whether to create a new ComputeDomain or use an existing one. If set to false, an existing ComputeDomain must be specified via the `Name` field. type: boolean name: description: Name of the ComputeDomain to use. Required if `Create` is false (i.e., using an existing ComputeDomain). type: string type: object x-kubernetes-validations: - message: if create is true, name must not be set; otherwise name is required. rule: '(has(self.create) && self.create) ? !has(self.name) : (has(self.name) && size(self.name) > 0)' mpi: description: MPI config for NIMService using LeaderWorkerSet properties: mpiStartTimeout: default: 300 description: MPIStartTimeout specifies the timeout in seconds for starting the cluster. type: integer required: - mpiStartTimeout type: object parallelism: description: Parallelism specifies the parallelism strategy for the multi-node NIMService. properties: pipeline: description: Pipeline specifies pipeline parallelism size for the multi-node NIMService. format: int32 minimum: 1 type: integer tensor: description: Tensor specifies tensor parallelism size for the multi-node NIMService. format: int32 minimum: 1 type: integer type: object required: - parallelism type: object nodeSelector: additionalProperties: type: string type: object podAffinity: description: 'Deprecated: Use Affinity instead.' properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object proxy: description: ProxySpec defines the proxy configuration for NIMService. properties: certConfigMap: type: string httpProxy: type: string httpsProxy: type: string noProxy: type: string type: object readinessProbe: description: Probe defines attributes for startup/liveness/readiness probes. properties: enabled: type: boolean probe: description: |- Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object type: object replicas: format: int32 minimum: 0 type: integer resources: description: |- Resources is the resource requirements for the NIMService deployment or leader worker set. Note: Only traditional resources like cpu/memory and custom device plugin resources are supported here. Any DRA claim references are ignored. Use DRAResources instead for those. properties: claims: description: |- Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. This field depends on the DynamicResourceAllocation feature gate. This field is immutable. It can only be set for containers. items: description: ResourceClaim references one entry in PodSpec.ResourceClaims. properties: name: description: |- Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. type: string request: description: |- Request is the name chosen for a request in the referenced claim. If empty, everything from the claim is made available, otherwise only the result of this request. type: string required: - name type: object type: array x-kubernetes-list-map-keys: - name x-kubernetes-list-type: map limits: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object runtimeClassName: type: string scale: description: Autoscaling defines attributes to automatically scale the service based on metrics. properties: annotations: additionalProperties: type: string type: object enabled: type: boolean hpa: description: HorizontalPodAutoscalerSpec defines the parameters required to setup HPA. properties: behavior: description: |- HorizontalPodAutoscalerBehavior configures the scaling behavior of the target in both Up and Down directions (scaleUp and scaleDown fields respectively). properties: scaleDown: description: |- scaleDown is scaling policy for scaling Down. If not set, the default value is to allow to scale down to minReplicas pods, with a 300 second stabilization window (i.e., the highest recommendation for the last 300sec is used). properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object scaleUp: description: |- scaleUp is scaling policy for scaling Up. If not set, the default value is the higher of: * increase no more than 4 pods per 60 seconds * double the number of pods per 60 seconds No stabilization is used. properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object type: object maxReplicas: format: int32 type: integer metrics: items: description: |- MetricSpec specifies how to scale based on a single metric (only `type` and one other matching field should be set at once). properties: containerResource: description: |- containerResource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing a single container in each pod of the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: container: description: container is the name of the container in the pods of the scaling target type: string name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - container - name - target type: object external: description: |- external refers to a global metric that is not associated with any Kubernetes object. It allows autoscaling based on information coming from components running outside of cluster (for example length of queue in cloud messaging service, or QPS from loadbalancer running outside of cluster). properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object object: description: |- object refers to a metric describing a single kubernetes object (for example, hits-per-second on an Ingress object). properties: describedObject: description: describedObject specifies the descriptions of a object,such as kind,name apiVersion properties: apiVersion: description: apiVersion is the API version of the referent type: string kind: description: 'kind is the kind of the referent; More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'name is the name of the referent; More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' type: string required: - kind - name type: object metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - describedObject - metric - target type: object pods: description: |- pods refers to a metric describing each pod in the current scale target (for example, transactions-processed-per-second). The values will be averaged together before being compared to the target value. properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object resource: description: |- resource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing each pod in the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - name - target type: object type: description: |- type is the type of metric source. It should be one of "ContainerResource", "External", "Object", "Pods" or "Resource", each mapping to a matching field in the object. type: string required: - type type: object type: array minReplicas: default: 1 format: int32 minimum: 1 type: integer required: - maxReplicas type: object type: object schedulerName: type: string sidecarContainers: items: description: NIMContainerSpec defines the specification for a container within a NIM workload. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object type: array startupProbe: description: Probe defines attributes for startup/liveness/readiness probes. properties: enabled: type: boolean probe: description: |- Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object type: object storage: description: Storage is the target storage for caching NIM model if NIMCache is not provided properties: emptyDir: description: EmptyDir is the empty dir volume used for caching NIM properties: sizeLimit: anyOf: - type: integer - type: string description: SizeLimit is the size limit of the empty dir volume pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object hostPath: description: HostPath is the host path volume for caching NIM type: string nimCache: description: NIMCacheVolSpec defines the spec to use NIMCache volume. properties: name: type: string profile: type: string type: object pvc: description: PersistentVolumeClaim is the pvc volume used for caching NIM properties: annotations: additionalProperties: type: string description: Annotations for the PVC type: object create: description: |- Create specifies whether to create a new PersistentVolumeClaim (PVC). If set to false, an existing PVC must be referenced via the `Name` field. type: boolean name: description: Name of the PVC to use. Required if `Create` is false (i.e., using an existing PVC). type: string size: description: Size of the NIM cache in Gi, used during PVC creation type: string storageClass: description: |- StorageClass to be used for PVC creation. Leave it as empty if the PVC is already created or a default storage class is set in the cluster. type: string subPath: description: SubPath is the path inside the PVC that should be mounted type: string volumeAccessMode: description: VolumeAccessMode is the volume access mode of the PVC type: string type: object readOnly: description: ReadOnly mode indicates if the volume should be mounted as read-only type: boolean sharedMemorySizeLimit: anyOf: - type: integer - type: string description: SharedMemorySizeLimit sets the max size of the shared memory volume (emptyDir) used by NIMs for fast model runtime I/O. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object tolerations: items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array userID: format: int64 type: integer required: - authSecret - image type: object x-kubernetes-validations: - message: autoScaling must be nil or disabled when multiNode is set rule: '!(has(self.multiNode) && has(self.scale) && has(self.scale.enabled) && self.scale.enabled)' - message: spec.replicas cannot be set when spec.scale.enabled is true rule: '!(has(self.scale) && has(self.scale.enabled) && self.scale.enabled && has(self.replicas))' - message: .spec.expose.ingress is deprecated, and will be removed in a future release. If .spec.expose.ingress is set, please do not set .spec.expose.router.ingress. rule: '!(has(self.expose) && has(self.expose.ingress) && has(self.expose.ingress.enabled) && self.expose.ingress.enabled && has(self.expose.router) && has(self.expose.router.ingress))' type: object type: array type: object status: description: NIMPipelineStatus defines the observed state of NIMPipeline. properties: conditions: description: |- INSERT ADDITIONAL STATUS FIELD - define observed state of cluster Important: Run "make" to regenerate code after modifying this file items: description: Condition contains details for one aspect of the current state of this API Resource. properties: lastTransitionTime: description: |- lastTransitionTime is the last time the condition transitioned from one status to another. This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable. format: date-time type: string message: description: |- message is a human readable message indicating details about the transition. This may be an empty string. maxLength: 32768 type: string observedGeneration: description: |- observedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date with respect to the current state of the instance. format: int64 minimum: 0 type: integer reason: description: |- reason contains a programmatic identifier indicating the reason for the condition's last transition. Producers of specific condition types may define expected values and meanings for this field, and whether the values are considered a guaranteed API. The value should be a CamelCase string. This field may not be empty. maxLength: 1024 minLength: 1 pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$ type: string status: description: status of the condition, one of True, False, Unknown. enum: - "True" - "False" - Unknown type: string type: description: type of condition in CamelCase or in foo.example.com/CamelCase. maxLength: 316 pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$ type: string required: - lastTransitionTime - message - reason - status - type type: object type: array state: description: State indicates the overall state of the pipeline type: string states: additionalProperties: type: string description: States indicate state of individual services in the pipeline type: object type: object type: object served: true storage: true subresources: status: {} --- # Source: k8s-nim-operator/crds/apps.nvidia.com_nimservices.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.0 name: nimservices.apps.nvidia.com spec: group: apps.nvidia.com names: kind: NIMService listKind: NIMServiceList plural: nimservices singular: nimservice scope: Namespaced versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - format: date-time jsonPath: .metadata.creationTimestamp name: Age type: date name: v1alpha1 schema: openAPIV3Schema: description: NIMService is the Schema for the nimservices API. properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string metadata: type: object spec: description: NIMServiceSpec defines the desired state of NIMService. properties: affinity: description: Affinity is a group of affinity scheduling rules. properties: nodeAffinity: description: Describes node affinity scheduling rules for the pod. properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. items: description: |- An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). properties: preference: description: A node selector term, associated with the corresponding weight. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic weight: description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. format: int32 type: integer required: - preference - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. properties: nodeSelectorTerms: description: Required. A list of node selector terms. The terms are ORed. items: description: |- A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic type: array x-kubernetes-list-type: atomic required: - nodeSelectorTerms type: object x-kubernetes-map-type: atomic type: object podAffinity: description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object podAntiAffinity: description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and subtracting "weight" from the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object type: object annotations: additionalProperties: type: string type: object args: items: type: string type: array authSecret: description: The name of an existing pull secret containing the NGC_API_KEY type: string command: items: type: string type: array draResources: description: DRAResources is the list of DRA resource claims to be used for the NIMService deployment or leader worker set. items: description: |- DRAResource references exactly one ResourceClaim, either directly or by naming a ResourceClaimTemplate which is then turned into a ResourceClaim. When creating the NIMService pods, it adds a name (`DNS_LABEL` format) to it that uniquely identifies the DRA resource. properties: claimCreationSpec: description: |- ClaimCreationSpec is the spec to auto-generate a DRA resource claim template. Only one of ClaimCreationSpec, ResourceClaimName or ResourceClaimTemplateName must be specified. properties: devices: items: properties: attributeSelectors: description: AttributeSelectors defines the criteria which must be satisfied by the device attributes of a device. items: description: DRADeviceAttributeSelector defines the selector expression for a DRA device attribute. properties: key: description: |- Key is the name of the device attribute. This is either a qualified name or a simple name. If it is a simple name, then it is assumed to be prefixed with the DRA driver name. Eg: "gpu.nvidia.com/productName" is equivalent to "productName" if the driver name is "gpu.nvidia.com". Otherwise they're treated as 2 different attributes. maxLength: 64 type: string op: default: Equal description: |- Op is the operator to use for comparing the device attribute value. Supported operators are: * Equal: The device attribute value must be equal to the value specified in the selector. * NotEqual: The device attribute value must not be equal to the value specified in the selector. * GreaterThan: The device attribute value must be greater than the value specified in the selector. * GreaterThanOrEqual: The device attribute value must be greater than or equal to the value specified in the selector. * LessThan: The device attribute value must be less than the value specified in the selector. * LessThanOrEqual: The device attribute value must be less than or equal to the value specified in the selector. enum: - Equal - NotEqual - GreaterThan - GreaterThanOrEqual - LessThan - LessThanOrEqual type: string value: description: Value is the value to compare against the device attribute. properties: boolValue: description: BoolValue is a true/false value. type: boolean intValue: description: IntValue is a number. format: int32 type: integer stringValue: description: StringValue is a string value. maxLength: 64 type: string versionValue: description: VersionValue is a semantic version according to semver.org spec 2.0.0. maxLength: 64 type: string type: object required: - key - op type: object type: array capacitySelectors: description: CapacitySelectors defines the criteria which must be satisfied by the device capacity of a device. items: description: DRAResourceQuantitySelector defines the selector expression for a DRA device capacity. properties: key: description: |- Key is the name of the resource. This is either a qualified name or a simple name. If it is a simple name, then it is assumed to be prefixed with the DRA driver name. Eg: "gpu.nvidia.com/memory" is equivalent to "memory" if the driver name is "gpu.nvidia.com". Otherwise they're treated as 2 different attributes. maxLength: 64 type: string op: default: Equal description: |- Op is the operator to use for comparing against the device capacity. Supported operators are: * Equal: The resource quantity value must be equal to the value specified in the selector. * NotEqual: The resource quantity value must not be equal to the value specified in the selector. * GreaterThan: The resource quantity value must be greater than the value specified in the selector. * GreaterThanOrEqual: The resource quantity value must be greater than or equal to the value specified in the selector. * LessThan: The resource quantity value must be less than the value specified in the selector. * LessThanOrEqual: The resource quantity value must be less than or equal to the value specified in the selector. enum: - Equal - NotEqual - GreaterThan - GreaterThanOrEqual - LessThan - LessThanOrEqual type: string value: anyOf: - type: integer - type: string description: Value is the resource quantity to compare against. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - key - op - value type: object type: array celExpressions: description: CELExpressions is a list of CEL expressions that must be satisfied by the DRA device. items: type: string type: array count: default: 1 description: Count is the number of devices to request. format: int32 type: integer deviceClassName: default: gpu.nvidia.com description: DeviceClassName references a specific DeviceClass to inherit configuration and selectors from. type: string driverName: default: gpu.nvidia.com description: |- DriverName is the name of the DRA driver providing the capacity information. Must be a DNS subdomain. maxLength: 253 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)* type: string name: description: |- Name is the name of the device request to use in the generated claim spec. Must be a valid DNS_LABEL. maxLength: 253 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)* type: string required: - count - deviceClassName - name type: object x-kubernetes-validations: - message: celExpressions must not be set if attributeSelectors or capacitySelectors are set rule: (has(self.celExpressions) && !(has(self.attributeSelectors) || has(self.capacitySelectors))) || !has(self.celExpressions) type: array generateName: description: GenerateName is an optional name prefix to use for generating the resource claim template. maxLength: 16 minLength: 1 type: string required: - devices type: object requests: description: |- Requests is the list of requests in the referenced DRA resource claim. to be made available to the model container of the NIMService pods. If empty, everything from the claim is made available, otherwise only the result of this subset of requests. items: minLength: 1 type: string type: array resourceClaimName: description: |- ResourceClaimName is the name of a DRA resource claim object in the same namespace as the NIMService. Exactly one of ResourceClaimName and ResourceClaimTemplateName must be set. maxLength: 253 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)* type: string resourceClaimTemplateName: description: |- ResourceClaimTemplateName is the name of a DRA resource claim template object in the same namespace as the pods for this NIMService. The template will be used to create a new DRA resource claim, which will be bound to the pods created for this NIMService. Exactly one of ResourceClaimName and ResourceClaimTemplateName must be set. maxLength: 253 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)* type: string type: object x-kubernetes-validations: - message: exactly one of spec.resourceClaimName, spec.resourceClaimTemplateName, or spec.claimCreationSpec must be set. rule: '(has(self.resourceClaimName) ? 1 : 0) + (has(self.resourceClaimTemplateName) ? 1 : 0) + (has(self.claimCreationSpec) ? 1 : 0) == 1' type: array env: items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array expose: description: Expose defines attributes to expose the service. properties: ingress: description: 'Deprecated: Use .spec.expose.router instead.' properties: annotations: additionalProperties: type: string type: object enabled: description: ingress, or virtualService - not both type: boolean spec: description: IngressSpec describes the Ingress the user wishes to exist. properties: defaultBackend: description: |- defaultBackend is the backend that should handle requests that don't match any rule. If Rules are not specified, DefaultBackend must be specified. If DefaultBackend is not set, the handling of requests that do not match any of the rules will be up to the Ingress controller. properties: resource: description: |- resource is an ObjectRef to another Kubernetes resource in the namespace of the Ingress object. If resource is specified, a service.Name and service.Port must not be specified. This is a mutually exclusive setting with "Service". properties: apiGroup: description: |- APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. type: string kind: description: Kind is the type of resource being referenced type: string name: description: Name is the name of resource being referenced type: string required: - kind - name type: object x-kubernetes-map-type: atomic service: description: |- service references a service as a backend. This is a mutually exclusive setting with "Resource". properties: name: description: |- name is the referenced service. The service must exist in the same namespace as the Ingress object. type: string port: description: |- port of the referenced service. A port name or port number is required for a IngressServiceBackend. properties: name: description: |- name is the name of the port on the Service. This is a mutually exclusive setting with "Number". type: string number: description: |- number is the numerical port number (e.g. 80) on the Service. This is a mutually exclusive setting with "Name". format: int32 type: integer type: object x-kubernetes-map-type: atomic required: - name type: object type: object ingressClassName: description: |- ingressClassName is the name of an IngressClass cluster resource. Ingress controller implementations use this field to know whether they should be serving this Ingress resource, by a transitive connection (controller -> IngressClass -> Ingress resource). Although the `kubernetes.io/ingress.class` annotation (simple constant name) was never formally defined, it was widely supported by Ingress controllers to create a direct binding between Ingress controller and Ingress resources. Newly created Ingress resources should prefer using the field. However, even though the annotation is officially deprecated, for backwards compatibility reasons, ingress controllers should still honor that annotation if present. type: string rules: description: |- rules is a list of host rules used to configure the Ingress. If unspecified, or no rule matches, all traffic is sent to the default backend. items: description: |- IngressRule represents the rules mapping the paths under a specified host to the related backend services. Incoming requests are first evaluated for a host match, then routed to the backend associated with the matching IngressRuleValue. properties: host: description: "host is the fully qualified domain name of a network host, as defined by RFC 3986.\nNote the following deviations from the \"host\" part of the\nURI as defined in RFC 3986:\n1. IPs are not allowed. Currently an IngressRuleValue can only apply to\n the IP in the Spec of the parent Ingress.\n2. The `:` delimiter is not respected because ports are not allowed.\n\t Currently the port of an Ingress is implicitly :80 for http and\n\t :443 for https.\nBoth these may change in the future.\nIncoming requests are matched against the host before the\nIngressRuleValue. If the host is unspecified, the Ingress routes all\ntraffic based on the specified IngressRuleValue.\n\nhost can be \"precise\" which is a domain name without the terminating dot of\na network host (e.g. \"foo.bar.com\") or \"wildcard\", which is a domain name\nprefixed with a single wildcard label (e.g. \"*.foo.com\").\nThe wildcard character '*' must appear by itself as the first DNS label and\nmatches only a single label. You cannot have a wildcard label by itself (e.g. Host == \"*\").\nRequests will be matched against the Host field in the following way:\n1. If host is precise, the request matches this rule if the http host header is equal to Host.\n2. If host is a wildcard, then the request matches this rule if the http host header\nis to equal to the suffix (removing the first label) of the wildcard rule." type: string http: description: |- HTTPIngressRuleValue is a list of http selectors pointing to backends. In the example: http:///? -> backend where where parts of the url correspond to RFC 3986, this resource will be used to match against everything after the last '/' and before the first '?' or '#'. properties: paths: description: paths is a collection of paths that map requests to backends. items: description: |- HTTPIngressPath associates a path with a backend. Incoming urls matching the path are forwarded to the backend. properties: backend: description: |- backend defines the referenced service endpoint to which the traffic will be forwarded to. properties: resource: description: |- resource is an ObjectRef to another Kubernetes resource in the namespace of the Ingress object. If resource is specified, a service.Name and service.Port must not be specified. This is a mutually exclusive setting with "Service". properties: apiGroup: description: |- APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. type: string kind: description: Kind is the type of resource being referenced type: string name: description: Name is the name of resource being referenced type: string required: - kind - name type: object x-kubernetes-map-type: atomic service: description: |- service references a service as a backend. This is a mutually exclusive setting with "Resource". properties: name: description: |- name is the referenced service. The service must exist in the same namespace as the Ingress object. type: string port: description: |- port of the referenced service. A port name or port number is required for a IngressServiceBackend. properties: name: description: |- name is the name of the port on the Service. This is a mutually exclusive setting with "Number". type: string number: description: |- number is the numerical port number (e.g. 80) on the Service. This is a mutually exclusive setting with "Name". format: int32 type: integer type: object x-kubernetes-map-type: atomic required: - name type: object type: object path: description: |- path is matched against the path of an incoming request. Currently it can contain characters disallowed from the conventional "path" part of a URL as defined by RFC 3986. Paths must begin with a '/' and must be present when using PathType with value "Exact" or "Prefix". type: string pathType: description: |- pathType determines the interpretation of the path matching. PathType can be one of the following values: * Exact: Matches the URL path exactly. * Prefix: Matches based on a URL path prefix split by '/'. Matching is done on a path element by element basis. A path element refers is the list of labels in the path split by the '/' separator. A request is a match for path p if every p is an element-wise prefix of p of the request path. Note that if the last element of the path is a substring of the last element in request path, it is not a match (e.g. /foo/bar matches /foo/bar/baz, but does not match /foo/barbaz). * ImplementationSpecific: Interpretation of the Path matching is up to the IngressClass. Implementations can treat this as a separate PathType or treat it identically to Prefix or Exact path types. Implementations are required to support all path types. type: string required: - backend - pathType type: object type: array x-kubernetes-list-type: atomic required: - paths type: object type: object type: array x-kubernetes-list-type: atomic tls: description: |- tls represents the TLS configuration. Currently the Ingress only supports a single TLS port, 443. If multiple members of this list specify different hosts, they will be multiplexed on the same port according to the hostname specified through the SNI TLS extension, if the ingress controller fulfilling the ingress supports SNI. items: description: IngressTLS describes the transport layer security associated with an ingress. properties: hosts: description: |- hosts is a list of hosts included in the TLS certificate. The values in this list must match the name/s used in the tlsSecret. Defaults to the wildcard host setting for the loadbalancer controller fulfilling this Ingress, if left unspecified. items: type: string type: array x-kubernetes-list-type: atomic secretName: description: |- secretName is the name of the secret used to terminate TLS traffic on port 443. Field is left optional to allow TLS routing based on SNI hostname alone. If the SNI host in a listener conflicts with the "Host" header field used by an IngressRule, the SNI host is used for termination and value of the "Host" header is used for routing. type: string type: object type: array x-kubernetes-list-type: atomic type: object type: object router: properties: annotations: additionalProperties: type: string description: Annotations for the router, e.g. for ingress class or gateway type: object eppConfig: description: EPPConfig is the configuration for the endpoint picker extension. This is field is currently only supported for standalone inference platform only on NIMService. properties: config: description: |- Config allows specifying EPP EndpointPickerConfig directly as a structured object. The operator will marshal this to YAML and create a ConfigMap automatically. Mutually exclusive with ConfigMapRef. One of ConfigMapRef or Config must be specified (no default configuration). Uses the upstream type from github.com/kubernetes-sigs/gateway-api-inference-extension properties: apiVersion: description: |- APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources type: string data: description: Data configures the DataLayer. It is required if the new DataLayer is enabled. properties: sources: description: Sources is the list of sources to define to the DataLayer items: description: DataLayerSource contains the configuration of a DataSource of the DataLayer feature properties: extractors: description: |- Extractors specifies the list of Plugin instances to be associated with this Source. The entries are references to the names of entries of the Plugins defined in the configuration's Plugins section items: description: DataLayerExtractor contains the configuration of an Extractor of the DataLayer feature properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Extractor. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - pluginRef type: object type: array pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this Source. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string required: - extractors - pluginRef type: object type: array required: - sources type: object featureGates: description: |- FeatureGates is a set of flags that enable various experimental features with the EPP. If omitted non of these experimental features will be enabled. items: type: string type: array kind: description: |- Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds type: string plugins: description: Plugins is the list of plugins that will be instantiated. items: description: |- PluginSpec contains the information that describes a plugin that will be instantiated. properties: name: description: |- Name provides a name for plugin entries to reference. If omitted, the value of the Plugin's Type field will be used. type: string parameters: description: |- Parameters are the set of parameters to be passed to the plugin's factory function. The factory function is responsible to parse the parameters. format: byte type: string type: description: Type specifies the plugin type to be instantiated. type: string required: - type type: object type: array saturationDetector: description: |- SaturationDetector when present specifies the configuration of the Saturation detector. If not present, default values are used. properties: kvCacheUtilThreshold: description: |- KVCacheUtilThreshold defines the KV cache utilization (0.0 to 1.0) above which a pod is considered to have insufficient capacity. type: number metricsStalenessThreshold: description: |- MetricsStalenessThreshold defines how old a pod's metrics can be. If a pod's metrics are older than this, it might be excluded from "good capacity" considerations or treated as having no capacity for safety. type: string queueDepthThreshold: description: |- QueueDepthThreshold defines the backend waiting queue size above which a pod is considered to have insufficient capacity for new requests. type: integer type: object schedulingProfiles: description: |- SchedulingProfiles is the list of named SchedulingProfiles that will be created. items: description: |- SchedulingProfile contains the information to create a SchedulingProfile entry to be used by the scheduler. properties: name: description: Name specifies the name of this SchedulingProfile type: string plugins: description: |- Plugins is the list of plugins for this SchedulingProfile. They are assigned to the appropriate "slots" based on their type. items: description: |- SchedulingPlugin describes a plugin that will be associated with a SchedulingProfile entry. properties: pluginRef: description: |- PluginRef specifies a partiular Plugin instance to be associated with this SchedulingProfile. The reference is to the name of an entry of the Plugins defined in the configuration's Plugins section type: string weight: description: Weight is the weight fo be used if this plugin is a Scorer. type: integer required: - pluginRef type: object type: array required: - name - plugins type: object type: array required: - plugins - schedulingProfiles type: object x-kubernetes-preserve-unknown-fields: true configMapRef: description: |- ConfigMapRef references a user-provided ConfigMap containing EPP configuration. The ConfigMap should contain EndpointPickerConfig YAML. Mutually exclusive with Config. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic containerSpec: description: ContainerSpec is the specification for the EPP container. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object livenessProbe: description: LivenessProbe is the liveness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object ports: description: Ports is the list of ports to expose for the EPP container. items: description: ContainerPort represents a network port in a single container. properties: containerPort: description: |- Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. format: int32 type: integer hostIP: description: What host IP to bind the external port to. type: string hostPort: description: |- Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. format: int32 type: integer name: description: |- If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. type: string protocol: default: TCP description: |- Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". type: string required: - containerPort type: object type: array readinessProbe: description: ReadinessProbe is the readiness probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object startupProbe: description: StartupProbe is the startup probe for the EPP container. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object required: - containerSpec type: object x-kubernetes-validations: - message: specify either configMapRef or config, not both rule: '!(has(self.configMapRef) && has(self.config))' gateway: description: Gateway is the gateway to use for the created HTTPRoute. properties: backendRef: description: BackendRef is a reference to a backend to forward matched requests to. properties: group: default: "" description: |- Group is the group of the referent. For example, "gateway.networking.k8s.io". When unspecified or empty string, core API group is inferred. maxLength: 253 pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ type: string kind: default: Service description: |- Kind is the Kubernetes resource kind of the referent. For example "Service". Defaults to "Service" when not specified. ExternalName services can refer to CNAME DNS records that may live outside of the cluster and as such are difficult to reason about in terms of conformance. They also may not be safe to forward to (see CVE-2021-25740 for more information). Implementations SHOULD NOT support ExternalName Services. Support: Core (Services with a type other than ExternalName) Support: Implementation-specific (Services with type ExternalName) maxLength: 63 minLength: 1 pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$ type: string name: description: Name is the name of the referent. maxLength: 253 minLength: 1 type: string namespace: description: |- Namespace is the namespace of the backend. When unspecified, the local namespace is inferred. Note that when a namespace different than the local namespace is specified, a ReferenceGrant object is required in the referent namespace to allow that namespace's owner to accept the reference. See the ReferenceGrant documentation for details. Support: Core maxLength: 63 minLength: 1 pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ type: string port: description: |- Port specifies the destination port number to use for this resource. Port is required when the referent is a Kubernetes Service. In this case, the port number is the service port number, not the target port. For other resources, destination port might be derived from the referent resource or this field. format: int32 maximum: 65535 minimum: 1 type: integer weight: default: 1 description: |- Weight specifies the proportion of requests forwarded to the referenced backend. This is computed as weight/(sum of all weights in this BackendRefs list). For non-zero values, there may be some epsilon from the exact proportion defined here depending on the precision an implementation supports. Weight is not a percentage and the sum of weights does not need to equal 100. If only one backend is specified and it has a weight greater than 0, 100% of the traffic is forwarded to that backend. If weight is set to 0, no traffic should be forwarded for this entry. If unspecified, weight defaults to 1. Support for this field varies based on the context where used. format: int32 maximum: 1000000 minimum: 0 type: integer required: - name type: object x-kubernetes-validations: - message: Must have port for Service reference rule: '(size(self.group) == 0 && self.kind == ''Service'') ? has(self.port) : true' grpcRoutesEnabled: default: false description: GRPCRoutesEnabled is a flag to enable GRPCRoutes for the created gateway. type: boolean httpRoutesEnabled: default: true description: HTTPRoutesEnabled is a flag to enable HTTPRoutes for the created gateway. type: boolean name: description: Name of the gateway minLength: 1 type: string namespace: description: Namespace of the gateway minLength: 1 type: string required: - name - namespace type: object hostDomainName: description: |- HostDomainName is the domain name of the hostname matched by the router. The hostname is constructed as "..", where the a subdomain of the matched hostname. eg. example.com for "..example.com" maxLength: 63 minLength: 1 pattern: ^(([a-z0-9][a-z0-9\-]*[a-z0-9])|[a-z0-9]+\.)*([a-z]+|xn\-\-[a-z0-9]+)\.?$ type: string ingress: description: Ingress is the ingress controller to use for the created ingress. properties: ingressClass: description: IngressClass is the ingress class to use for the created ingress. minLength: 1 type: string tlsSecretName: description: TLSSecretName is the name of the secret containing the TLS certificate and key. type: string required: - ingressClass type: object type: object x-kubernetes-validations: - message: ingress and gateway cannot be specified together rule: '!(has(self.gateway) && has(self.ingress))' service: description: Service defines attributes to create a service. properties: annotations: additionalProperties: type: string type: object grpcPort: description: |- GRPCPort is the GRPC serving port Note: This port is only applicable for NIMs that runs a Triton GRPC Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer metricsPort: description: |- MetricsPort is the port for metrics Note: This port is only applicable for NIMs that runs a separate metrics endpoint on Triton Inference Server. format: int32 maximum: 65535 minimum: 1 type: integer name: description: Override the default service name type: string port: default: 8000 description: 'Port is the main api serving port (default: 8000)' format: int32 maximum: 65535 minimum: 1 type: integer type: description: Service Type string describes ingress methods for a service type: string type: object type: object groupID: format: int64 type: integer image: description: Image defines image attributes. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object inferencePlatform: default: standalone description: |- InferencePlatform specifies the inference platform to use for this NIMService. Valid values are "standalone" (default) and "kserve". enum: - standalone - kserve type: string initContainers: items: description: NIMContainerSpec defines the specification for a container within a NIM workload. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object type: array labels: additionalProperties: type: string type: object livenessProbe: description: Probe defines attributes for startup/liveness/readiness probes. properties: enabled: type: boolean probe: description: |- Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object type: object metrics: description: Metrics defines attributes to setup metrics collection. properties: enabled: type: boolean serviceMonitor: description: for use with the Prometheus Operator and the primary service object properties: additionalLabels: additionalProperties: type: string type: object annotations: additionalProperties: type: string type: object interval: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string scrapeTimeout: description: |- Duration is a valid time duration that can be parsed by Prometheus model.ParseDuration() function. Supported units: y, w, d, h, m, s, ms Examples: `30s`, `1m`, `1h20m15s`, `15d` pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string type: object type: object multiNode: description: NimServiceMultiNodeConfig defines the configuration for multi-node NIMService. properties: backendType: default: lws description: BackendType specifies the backend type for the multi-node NIMService. Currently only LWS is supported. enum: - lws type: string computeDomain: description: |- ComputeDomain specifies the compute domain to use for a multi-node NIMService. properties: create: description: |- Create specifies whether to create a new ComputeDomain or use an existing one. If set to false, an existing ComputeDomain must be specified via the `Name` field. type: boolean name: description: Name of the ComputeDomain to use. Required if `Create` is false (i.e., using an existing ComputeDomain). type: string type: object x-kubernetes-validations: - message: if create is true, name must not be set; otherwise name is required. rule: '(has(self.create) && self.create) ? !has(self.name) : (has(self.name) && size(self.name) > 0)' mpi: description: MPI config for NIMService using LeaderWorkerSet properties: mpiStartTimeout: default: 300 description: MPIStartTimeout specifies the timeout in seconds for starting the cluster. type: integer required: - mpiStartTimeout type: object parallelism: description: Parallelism specifies the parallelism strategy for the multi-node NIMService. properties: pipeline: description: Pipeline specifies pipeline parallelism size for the multi-node NIMService. format: int32 minimum: 1 type: integer tensor: description: Tensor specifies tensor parallelism size for the multi-node NIMService. format: int32 minimum: 1 type: integer type: object required: - parallelism type: object nodeSelector: additionalProperties: type: string type: object podAffinity: description: 'Deprecated: Use Affinity instead.' properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. items: description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) properties: podAffinityTerm: description: Required. A pod affinity term, associated with the corresponding weight. properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object weight: description: |- weight associated with matching the corresponding podAffinityTerm, in the range 1-100. format: int32 type: integer required: - podAffinityTerm - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. items: description: |- Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running properties: labelSelector: description: |- A label query over a set of resources, in this case pods. If it's null, this PodAffinityTerm matches with no Pods. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic matchLabelKeys: description: |- MatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key in (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both matchLabelKeys and labelSelector. Also, matchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic mismatchLabelKeys: description: |- MismatchLabelKeys is a set of pod label keys to select which pods will be taken into consideration. The keys are used to lookup values from the incoming pod labels, those key-value labels are merged with `labelSelector` as `key notin (value)` to select the group of existing pods which pods will be taken into consideration for the incoming pod's pod (anti) affinity. Keys that don't exist in the incoming pod labels will be ignored. The default value is empty. The same key is forbidden to exist in both mismatchLabelKeys and labelSelector. Also, mismatchLabelKeys cannot be set when labelSelector isn't set. items: type: string type: array x-kubernetes-list-type: atomic namespaceSelector: description: |- A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic namespaces: description: |- namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". items: type: string type: array x-kubernetes-list-type: atomic topologyKey: description: |- This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. type: string required: - topologyKey type: object type: array x-kubernetes-list-type: atomic type: object proxy: description: ProxySpec defines the proxy configuration for NIMService. properties: certConfigMap: type: string httpProxy: type: string httpsProxy: type: string noProxy: type: string type: object readinessProbe: description: Probe defines attributes for startup/liveness/readiness probes. properties: enabled: type: boolean probe: description: |- Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object type: object replicas: format: int32 minimum: 0 type: integer resources: description: |- Resources is the resource requirements for the NIMService deployment or leader worker set. Note: Only traditional resources like cpu/memory and custom device plugin resources are supported here. Any DRA claim references are ignored. Use DRAResources instead for those. properties: claims: description: |- Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. This field depends on the DynamicResourceAllocation feature gate. This field is immutable. It can only be set for containers. items: description: ResourceClaim references one entry in PodSpec.ResourceClaims. properties: name: description: |- Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. type: string request: description: |- Request is the name chosen for a request in the referenced claim. If empty, everything from the claim is made available, otherwise only the result of this request. type: string required: - name type: object type: array x-kubernetes-list-map-keys: - name x-kubernetes-list-type: map limits: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: additionalProperties: anyOf: - type: integer - type: string pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true description: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object runtimeClassName: type: string scale: description: Autoscaling defines attributes to automatically scale the service based on metrics. properties: annotations: additionalProperties: type: string type: object enabled: type: boolean hpa: description: HorizontalPodAutoscalerSpec defines the parameters required to setup HPA. properties: behavior: description: |- HorizontalPodAutoscalerBehavior configures the scaling behavior of the target in both Up and Down directions (scaleUp and scaleDown fields respectively). properties: scaleDown: description: |- scaleDown is scaling policy for scaling Down. If not set, the default value is to allow to scale down to minReplicas pods, with a 300 second stabilization window (i.e., the highest recommendation for the last 300sec is used). properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object scaleUp: description: |- scaleUp is scaling policy for scaling Up. If not set, the default value is the higher of: * increase no more than 4 pods per 60 seconds * double the number of pods per 60 seconds No stabilization is used. properties: policies: description: |- policies is a list of potential scaling polices which can be used during scaling. If not set, use the default values: - For scale up: allow doubling the number of pods, or an absolute change of 4 pods in a 15s window. - For scale down: allow all pods to be removed in a 15s window. items: description: HPAScalingPolicy is a single policy which must hold true for a specified past interval. properties: periodSeconds: description: |- periodSeconds specifies the window of time for which the policy should hold true. PeriodSeconds must be greater than zero and less than or equal to 1800 (30 min). format: int32 type: integer type: description: type is used to specify the scaling policy. type: string value: description: |- value contains the amount of change which is permitted by the policy. It must be greater than zero format: int32 type: integer required: - periodSeconds - type - value type: object type: array x-kubernetes-list-type: atomic selectPolicy: description: |- selectPolicy is used to specify which policy should be used. If not set, the default value Max is used. type: string stabilizationWindowSeconds: description: |- stabilizationWindowSeconds is the number of seconds for which past recommendations should be considered while scaling up or scaling down. StabilizationWindowSeconds must be greater than or equal to zero and less than or equal to 3600 (one hour). If not set, use the default values: - For scale up: 0 (i.e. no stabilization is done). - For scale down: 300 (i.e. the stabilization window is 300 seconds long). format: int32 type: integer tolerance: anyOf: - type: integer - type: string description: |- tolerance is the tolerance on the ratio between the current and desired metric value under which no updates are made to the desired number of replicas (e.g. 0.01 for 1%). Must be greater than or equal to zero. If not set, the default cluster-wide tolerance is applied (by default 10%). For example, if autoscaling is configured with a memory consumption target of 100Mi, and scale-down and scale-up tolerances of 5% and 1% respectively, scaling will be triggered when the actual consumption falls below 95Mi or exceeds 101Mi. This is an alpha field and requires enabling the HPAConfigurableTolerance feature gate. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object type: object maxReplicas: format: int32 type: integer metrics: items: description: |- MetricSpec specifies how to scale based on a single metric (only `type` and one other matching field should be set at once). properties: containerResource: description: |- containerResource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing a single container in each pod of the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: container: description: container is the name of the container in the pods of the scaling target type: string name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - container - name - target type: object external: description: |- external refers to a global metric that is not associated with any Kubernetes object. It allows autoscaling based on information coming from components running outside of cluster (for example length of queue in cloud messaging service, or QPS from loadbalancer running outside of cluster). properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object object: description: |- object refers to a metric describing a single kubernetes object (for example, hits-per-second on an Ingress object). properties: describedObject: description: describedObject specifies the descriptions of a object,such as kind,name apiVersion properties: apiVersion: description: apiVersion is the API version of the referent type: string kind: description: 'kind is the kind of the referent; More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'name is the name of the referent; More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' type: string required: - kind - name type: object metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - describedObject - metric - target type: object pods: description: |- pods refers to a metric describing each pod in the current scale target (for example, transactions-processed-per-second). The values will be averaged together before being compared to the target value. properties: metric: description: metric identifies the target metric by name and selector properties: name: description: name is the name of the given metric type: string selector: description: |- selector is the string-encoded form of a standard kubernetes label selector for the given metric When set, it is passed as an additional parameter to the metrics server for more specific metrics scoping. When unset, just the metricName will be used to gather metrics. properties: matchExpressions: description: matchExpressions is a list of label selector requirements. The requirements are ANDed. items: description: |- A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: key is the label key that the selector applies to. type: string operator: description: |- operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. type: string values: description: |- values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchLabels: additionalProperties: type: string description: |- matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. type: object type: object x-kubernetes-map-type: atomic required: - name type: object target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - metric - target type: object resource: description: |- resource refers to a resource metric (such as those specified in requests and limits) known to Kubernetes describing each pod in the current scale target (e.g. CPU or memory). Such metrics are built in to Kubernetes, and have special scaling options on top of those available to normal per-pod metrics using the "pods" source. properties: name: description: name is the name of the resource in question. type: string target: description: target specifies the target value for the given metric properties: averageUtilization: description: |- averageUtilization is the target value of the average of the resource metric across all relevant pods, represented as a percentage of the requested value of the resource for the pods. Currently only valid for Resource metric source type format: int32 type: integer averageValue: anyOf: - type: integer - type: string description: |- averageValue is the target value of the average of the metric across all relevant pods (as a quantity) pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: description: type represents whether the metric type is Utilization, Value, or AverageValue type: string value: anyOf: - type: integer - type: string description: value is the target value of the metric (as a quantity). pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true required: - type type: object required: - name - target type: object type: description: |- type is the type of metric source. It should be one of "ContainerResource", "External", "Object", "Pods" or "Resource", each mapping to a matching field in the object. type: string required: - type type: object type: array minReplicas: default: 1 format: int32 minimum: 1 type: integer required: - maxReplicas type: object type: object schedulerName: type: string sidecarContainers: items: description: NIMContainerSpec defines the specification for a container within a NIM workload. properties: args: description: Args are the arguments passed to the container command at runtime. items: type: string type: array command: description: Command is the entrypoint array. If not specified, the image's default entrypoint is used. items: type: string type: array env: description: Env is the list of environment variables to set in the container. items: description: EnvVar represents an environment variable present in a Container. properties: name: description: |- Name of the environment variable. May consist of any printable ASCII characters except '='. type: string value: description: |- Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "". type: string valueFrom: description: Source for the environment variable's value. Cannot be used if value is not empty. properties: configMapKeyRef: description: Selects a key of a ConfigMap. properties: key: description: The key to select. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the ConfigMap or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic fieldRef: description: |- Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['']`, `metadata.annotations['']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs. properties: apiVersion: description: Version of the schema the FieldPath is written in terms of, defaults to "v1". type: string fieldPath: description: Path of the field to select in the specified API version. type: string required: - fieldPath type: object x-kubernetes-map-type: atomic fileKeyRef: description: |- FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate to be enabled. properties: key: description: |- The key within the env file. An invalid key will prevent the pod from starting. The keys defined within a source may consist of any printable ASCII characters except '='. During Alpha stage of the EnvFiles feature gate, the key size is limited to 128 characters. type: string optional: default: false description: |- Specify whether the file or its key must be defined. If the file or key does not exist, then the env var is not published. If optional is set to true and the specified key does not exist, the environment variable will not be set in the Pod's containers. If optional is set to false and the specified key does not exist, an error will be returned during Pod creation. type: boolean path: description: |- The path within the volume from which to select the file. Must be relative and may not contain the '..' path or start with '..'. type: string volumeName: description: The name of the volume mount containing the env file. type: string required: - key - path - volumeName type: object x-kubernetes-map-type: atomic resourceFieldRef: description: |- Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported. properties: containerName: description: 'Container name: required for volumes, optional for env vars' type: string divisor: anyOf: - type: integer - type: string description: Specifies the output format of the exposed resources, defaults to "1" pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true resource: description: 'Required: resource to select' type: string required: - resource type: object x-kubernetes-map-type: atomic secretKeyRef: description: Selects a key of a secret in the pod's namespace properties: key: description: The key of the secret to select from. Must be a valid secret key. type: string name: default: "" description: |- Name of the referent. This field is effectively required, but due to backwards compatibility is allowed to be empty. Instances of this type with an empty value here are almost certainly wrong. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names type: string optional: description: Specify whether the Secret or its key must be defined type: boolean required: - key type: object x-kubernetes-map-type: atomic type: object required: - name type: object type: array image: description: Image specifies the container image to run. properties: pullPolicy: type: string pullSecrets: items: type: string type: array repository: type: string tag: type: string required: - repository - tag type: object name: description: Name is the unique name of the container within the pod. type: string workingDir: description: WorkingDir is the container's working directory. If unset, the container runtime's default is used. type: string required: - image - name type: object type: array startupProbe: description: Probe defines attributes for startup/liveness/readiness probes. properties: enabled: type: boolean probe: description: |- Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. properties: exec: description: Exec specifies a command to execute in the container. properties: command: description: |- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. items: type: string type: array x-kubernetes-list-type: atomic type: object failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 type: integer grpc: description: GRPC specifies a GRPC HealthCheckRequest. properties: port: description: Port number of the gRPC service. Number must be in the range 1 to 65535. format: int32 type: integer service: default: "" description: |- Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). If this is not specified, the default behavior is defined by gRPC. type: string required: - port type: object httpGet: description: HTTPGet specifies an HTTP GET request to perform. properties: host: description: |- Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. type: string httpHeaders: description: Custom headers to set in the request. HTTP allows repeated headers. items: description: HTTPHeader describes a custom header to be used in HTTP probes properties: name: description: |- The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. type: string value: description: The header field value type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic path: description: Path to access on the HTTP server. type: string port: anyOf: - type: integer - type: string description: |- Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true scheme: description: |- Scheme to use for connecting to the host. Defaults to HTTP. type: string required: - port type: object initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 type: integer tcpSocket: description: TCPSocket specifies a connection to a TCP port. properties: host: description: 'Optional: Host name to connect to, defaults to the pod IP.' type: string port: anyOf: - type: integer - type: string description: |- Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. x-kubernetes-int-or-string: true required: - port type: object terminationGracePeriodSeconds: description: |- Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. format: int64 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer type: object type: object storage: description: Storage is the target storage for caching NIM model if NIMCache is not provided properties: emptyDir: description: EmptyDir is the empty dir volume used for caching NIM properties: sizeLimit: anyOf: - type: integer - type: string description: SizeLimit is the size limit of the empty dir volume pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object hostPath: description: HostPath is the host path volume for caching NIM type: string nimCache: description: NIMCacheVolSpec defines the spec to use NIMCache volume. properties: name: type: string profile: type: string type: object pvc: description: PersistentVolumeClaim is the pvc volume used for caching NIM properties: annotations: additionalProperties: type: string description: Annotations for the PVC type: object create: description: |- Create specifies whether to create a new PersistentVolumeClaim (PVC). If set to false, an existing PVC must be referenced via the `Name` field. type: boolean name: description: Name of the PVC to use. Required if `Create` is false (i.e., using an existing PVC). type: string size: description: Size of the NIM cache in Gi, used during PVC creation type: string storageClass: description: |- StorageClass to be used for PVC creation. Leave it as empty if the PVC is already created or a default storage class is set in the cluster. type: string subPath: description: SubPath is the path inside the PVC that should be mounted type: string volumeAccessMode: description: VolumeAccessMode is the volume access mode of the PVC type: string type: object readOnly: description: ReadOnly mode indicates if the volume should be mounted as read-only type: boolean sharedMemorySizeLimit: anyOf: - type: integer - type: string description: SharedMemorySizeLimit sets the max size of the shared memory volume (emptyDir) used by NIMs for fast model runtime I/O. pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ x-kubernetes-int-or-string: true type: object tolerations: items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array userID: format: int64 type: integer required: - authSecret - image type: object x-kubernetes-validations: - message: spec.draResources is immutable rule: (has(self.draResources) && has(oldSelf.draResources) && self.draResources == oldSelf.draResources) || (!has(self.draResources) && !has(oldSelf.draResources)) - message: autoScaling must be nil or disabled when multiNode is set rule: '!(has(self.multiNode) && has(self.scale) && has(self.scale.enabled) && self.scale.enabled)' - message: spec.replicas cannot be set when spec.scale.enabled is true rule: '!(has(self.scale) && has(self.scale.enabled) && self.scale.enabled && has(self.replicas))' - message: .spec.expose.ingress is deprecated, and will be removed in a future release. If .spec.expose.ingress is set, please do not set .spec.expose.router.ingress. rule: '!(has(self.expose) && has(self.expose.ingress) && has(self.expose.ingress.enabled) && self.expose.ingress.enabled && has(self.expose.router) && has(self.expose.router.ingress))' status: description: NIMServiceStatus defines the observed state of NIMService. properties: availableReplicas: format: int32 type: integer computeDomainStatus: description: ComputeDomainStatus is the status of the ComputeDomain for a multi-node NIMService. properties: name: type: string nodes: items: description: ComputeDomainStatus defines the status of a node in the ComputeDomain. properties: cliqueID: description: CliqueID is the clique ID of the NVLink domain. type: string name: description: Name is the name of the node. type: string status: default: NotReady description: |- Status tracks the readiness of the IMEX daemon running on this node. * Ready: the IMEX daemon is ready to broker GPU memory exchanges. * NotReady: the IMEX daemon is not ready to broker GPU memory exchanges. enum: - Ready - NotReady type: string required: - cliqueID - name type: object type: array status: type: string required: - name type: object conditions: items: description: Condition contains details for one aspect of the current state of this API Resource. properties: lastTransitionTime: description: |- lastTransitionTime is the last time the condition transitioned from one status to another. This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable. format: date-time type: string message: description: |- message is a human readable message indicating details about the transition. This may be an empty string. maxLength: 32768 type: string observedGeneration: description: |- observedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date with respect to the current state of the instance. format: int64 minimum: 0 type: integer reason: description: |- reason contains a programmatic identifier indicating the reason for the condition's last transition. Producers of specific condition types may define expected values and meanings for this field, and whether the values are considered a guaranteed API. The value should be a CamelCase string. This field may not be empty. maxLength: 1024 minLength: 1 pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$ type: string status: description: status of the condition, one of True, False, Unknown. enum: - "True" - "False" - Unknown type: string type: description: type of condition in CamelCase or in foo.example.com/CamelCase. maxLength: 316 pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$ type: string required: - lastTransitionTime - message - reason - status - type type: object type: array draResourceStatuses: description: DRAResourceStatuses is the status of the DRA resources. items: description: DRAResourceStatus defines the status of the DRAResource. properties: name: description: Name is the pod claim name referenced in the pod spec as `spec.resourceClaims[].name` for this DRA resource. type: string resourceClaimStatus: description: |- ResourceClaimStatus is the status of the resource claim in this DRA resource. Exactly one of resourceClaimStatus and resourceClaimTemplateStatus will be set. properties: name: description: Name is the name of the ResourceClaim. type: string state: description: |- State is the state of the ResourceClaim. * pending: the resource claim is pending allocation. * deleted: the resource claim has a deletion timestamp set but is not yet finalized. * allocated: the resource claim is allocated to a pod. * reserved: the resource claim is consumed by a pod. This field will have one or more of the above values depending on the status of the resource claim. type: string required: - name - state type: object resourceClaimTemplateStatus: description: |- ResourceClaimTemplateStatus is the status of the resource claim template in this DRA resource. Exactly one of resourceClaimStatus and resourceClaimTemplateStatus will be set. properties: name: description: Name is the name of the resource claim template. type: string resourceClaimStatuses: description: ResourceClaimStatuses is the statuses of the generated resource claims from this resource claim template. items: description: DRAResourceClaimStatusInfo defines the status of a ResourceClaim referenced in the DRAResource. properties: name: description: Name is the name of the ResourceClaim. type: string state: description: |- State is the state of the ResourceClaim. * pending: the resource claim is pending allocation. * deleted: the resource claim has a deletion timestamp set but is not yet finalized. * allocated: the resource claim is allocated to a pod. * reserved: the resource claim is consumed by a pod. This field will have one or more of the above values depending on the status of the resource claim. type: string required: - name - state type: object type: array required: - name type: object required: - name type: object x-kubernetes-validations: - message: exactly one of resourceClaimStatus and resourceClaimTemplateStatus must be set. rule: has(self.resourceClaimStatus) != has(self.resourceClaimTemplateStatus) type: array x-kubernetes-list-map-keys: - name x-kubernetes-list-type: map model: description: ModelStatus defines the configuration of the NIMService model. properties: clusterEndpoint: type: string externalEndpoint: type: string name: type: string required: - clusterEndpoint - externalEndpoint - name type: object state: type: string type: object type: object served: true storage: true subresources: status: {} --- # Source: k8s-nim-operator/templates/serviceaccount.yaml apiVersion: v1 kind: ServiceAccount metadata: name: k8s-nim-operator labels: app.kubernetes.io/component: rbac app.kubernetes.io/created-by: k8s-nim-operator app.kubernetes.io/part-of: k8s-nim-operator helm.sh/chart: k8s-nim-operator-3.1.0 app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator app.kubernetes.io/version: "3.1.0" app.kubernetes.io/managed-by: Helm annotations: {} --- # Source: k8s-nim-operator/templates/manager-rbac.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: name: k8s-nim-operator-role labels: helm.sh/chart: k8s-nim-operator-3.1.0 app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator app.kubernetes.io/version: "3.1.0" app.kubernetes.io/managed-by: Helm rules: - apiGroups: - "" resources: - nodes verbs: - get - list - watch - apiGroups: - "" resources: - configmaps - persistentvolumeclaims - secrets verbs: - create - delete - get - list - patch - update - watch - apiGroups: - "" resources: - events verbs: - get - list - create - update - patch - watch - apiGroups: - "" resources: - endpoints - pods - pods/log - pods/eviction - serviceaccounts - services - services/finalizers verbs: - create - delete - get - list - patch - update - watch - apiGroups: - "" resources: - pods verbs: - create - delete - get - list - watch - apiGroups: - apps resources: - deployments - statefulsets verbs: - create - delete - get - list - patch - update - watch - apiGroups: - apps.nvidia.com resources: - nemocustomizers verbs: - create - delete - get - list - patch - update - watch - apiGroups: - apps.nvidia.com resources: - nemocustomizers/finalizers verbs: - update - apiGroups: - apps.nvidia.com resources: - nemocustomizers/status verbs: - get - patch - update - apiGroups: - apps.nvidia.com resources: - nemoguardrails verbs: - create - delete - get - list - patch - update - watch - apiGroups: - apps.nvidia.com resources: - nemoguardrails/finalizers verbs: - update - apiGroups: - apps.nvidia.com resources: - nemoguardrails/status verbs: - get - patch - update - apiGroups: - apps.nvidia.com resources: - nemodatastores verbs: - create - delete - get - list - patch - update - watch - apiGroups: - apps.nvidia.com resources: - nemodatastores/finalizers verbs: - update - apiGroups: - apps.nvidia.com resources: - nemodatastores/status verbs: - get - patch - update - apiGroups: - apps.nvidia.com resources: - nemoevaluators verbs: - create - delete - get - list - patch - update - watch - apiGroups: - apps.nvidia.com resources: - nemoevaluators/finalizers verbs: - update - apiGroups: - apps.nvidia.com resources: - nemoevaluators/status verbs: - get - patch - update - apiGroups: - apps.nvidia.com resources: - nemoentitystores verbs: - create - delete - get - list - patch - update - watch - apiGroups: - apps.nvidia.com resources: - nemoentitystores/finalizers verbs: - update - apiGroups: - apps.nvidia.com resources: - nemoentitystores/status verbs: - get - patch - update - apiGroups: - apps.nvidia.com resources: - nimcaches verbs: - create - delete - get - list - patch - update - watch - apiGroups: - apps.nvidia.com resources: - nimcaches/finalizers verbs: - update - apiGroups: - apps.nvidia.com resources: - nimcaches/status verbs: - get - patch - update - apiGroups: - apps.nvidia.com resources: - nimbuilds verbs: - create - delete - get - list - patch - update - watch - apiGroups: - apps.nvidia.com resources: - nimbuilds/finalizers verbs: - update - apiGroups: - apps.nvidia.com resources: - nimbuilds/status verbs: - get - patch - update - apiGroups: - apps.nvidia.com resources: - nimpipelines verbs: - create - delete - get - list - patch - update - watch - apiGroups: - apps.nvidia.com resources: - nimpipelines/finalizers verbs: - update - apiGroups: - apps.nvidia.com resources: - nimpipelines/status verbs: - get - patch - update - apiGroups: - apps.nvidia.com resources: - nimservices verbs: - create - delete - get - list - patch - update - watch - apiGroups: - apps.nvidia.com resources: - nimservices/finalizers verbs: - update - apiGroups: - apps.nvidia.com resources: - nimservices/status verbs: - get - patch - update - apiGroups: - batch resources: - jobs verbs: - create - delete - get - list - patch - update - watch - apiGroups: - batch resources: - jobs/status verbs: - get - list - watch - apiGroups: - config.openshift.io resources: - clusterversions - proxies verbs: - get - list - watch - apiGroups: - "" resources: - persistentvolumeclaims verbs: - create - delete - get - list - apiGroups: - monitoring.coreos.com resources: - prometheusrules - servicemonitors verbs: - create - delete - get - list - patch - update - watch - apiGroups: - rbac.authorization.k8s.io resources: - rolebindings - roles verbs: - create - delete - get - list - patch - update - watch - apiGroups: - resource.k8s.io resources: - resourceclaims - resourceclaimtemplates verbs: - get - list - watch - create - delete - apiGroups: - route.openshift.io resources: - routes verbs: - create - get - list - patch - update - watch - apiGroups: - networking.k8s.io resources: - ingresses verbs: - create - get - list - patch - update - watch - delete - apiGroups: - autoscaling resources: - horizontalpodautoscalers verbs: - create - delete - get - list - patch - update - watch - apiGroups: - scheduling.k8s.io resources: - priorityclasses verbs: - create - get - list - watch - apiGroups: - security.openshift.io resourceNames: - nonroot - anyuid - hostmount-anyuid resources: - securitycontextconstraints verbs: - use - apiGroups: - security.openshift.io resources: - securitycontextconstraints verbs: - create - delete - get - list - patch - update - watch - apiGroups: - storage.k8s.io resources: - storageclasses verbs: - get - list - watch - apiGroups: - authentication.k8s.io resources: - tokenreviews verbs: - create - apiGroups: - authorization.k8s.io resources: - subjectaccessreviews verbs: - create - apiGroups: - batch.volcano.sh resources: - jobs verbs: - create - delete - get - list - patch - update - watch - apiGroups: - batch.volcano.sh resources: - jobs/status verbs: - get - list - watch - apiGroups: - nvidia.com resources: - nemoentityhandlers - nemotrainingjobs - nemotrainingjobs/status verbs: - create - delete - get - list - patch - update - watch - apiGroups: - scheduling.incubator.k8s.io - scheduling.volcano.sh resources: - podgroups - queues - queues/status verbs: - get - list - watch - apiGroups: - nodeinfo.volcano.sh resources: - numatopologies verbs: - get - list - watch - apiGroups: - run.ai resources: - trainingworkloads - runaijobs verbs: - get - list - watch - delete - patch - update - apiGroups: - leaderworkerset.x-k8s.io resources: - leaderworkersets verbs: - create - get - list - watch - delete - patch - update - apiGroups: - serving.kserve.io resources: - inferenceservices verbs: - create - delete - get - list - patch - update - watch - apiGroups: - leaderworkerset.x-k8s.io resources: - leaderworkersets verbs: - create - get - list - watch - delete - patch - update - apiGroups: - admissionregistration.k8s.io resources: - validatingwebhookconfigurations verbs: - get - list - watch - patch - update - apiGroups: - gateway.networking.k8s.io resources: - httproutes - grpcroutes verbs: - create - delete - get - list - patch - update - watch - apiGroups: - resource.nvidia.com resources: - computedomains verbs: - create - delete - get - list - patch - update - watch - apiGroups: - inference.networking.k8s.io resources: - inferencepools - inferenceobjectives verbs: - create - delete - get - list - patch - update - watch - apiGroups: - inference.networking.x-k8s.io resources: - inferencepools - inferenceobjectives verbs: - create - delete - get - list - patch - update - watch --- # Source: k8s-nim-operator/templates/metrics-reader-rbac.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: name: k8s-nim-operator-metrics-reader labels: app.kubernetes.io/component: kube-rbac-proxy app.kubernetes.io/created-by: k8s-nim-operator app.kubernetes.io/part-of: k8s-nim-operator helm.sh/chart: k8s-nim-operator-3.1.0 app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator app.kubernetes.io/version: "3.1.0" app.kubernetes.io/managed-by: Helm rules: - nonResourceURLs: - /metrics verbs: - get --- # Source: k8s-nim-operator/templates/manager-rbac.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: name: k8s-nim-operator-rolebinding labels: app.kubernetes.io/component: rbac app.kubernetes.io/created-by: k8s-nim-operator app.kubernetes.io/part-of: k8s-nim-operator helm.sh/chart: k8s-nim-operator-3.1.0 app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator app.kubernetes.io/version: "3.1.0" app.kubernetes.io/managed-by: Helm roleRef: apiGroup: rbac.authorization.k8s.io kind: ClusterRole name: k8s-nim-operator-role subjects: - kind: ServiceAccount name: k8s-nim-operator namespace: nvidia-nim --- # Source: k8s-nim-operator/templates/leader-election-rbac.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: Role metadata: name: k8s-nim-operator-leader-election-role labels: app.kubernetes.io/component: rbac app.kubernetes.io/created-by: k8s-nim-operator app.kubernetes.io/part-of: k8s-nim-operator helm.sh/chart: k8s-nim-operator-3.1.0 app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator app.kubernetes.io/version: "3.1.0" app.kubernetes.io/managed-by: Helm rules: - apiGroups: - "" resources: - configmaps verbs: - get - list - watch - create - update - patch - delete - apiGroups: - coordination.k8s.io resources: - leases verbs: - get - list - watch - create - update - patch - delete - apiGroups: - "" resources: - events verbs: - create - patch --- # Source: k8s-nim-operator/templates/leader-election-rbac.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: RoleBinding metadata: name: k8s-nim-operator-leader-election-rolebinding labels: app.kubernetes.io/component: rbac app.kubernetes.io/created-by: k8s-nim-operator app.kubernetes.io/part-of: k8s-nim-operator helm.sh/chart: k8s-nim-operator-3.1.0 app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator app.kubernetes.io/version: "3.1.0" app.kubernetes.io/managed-by: Helm roleRef: apiGroup: rbac.authorization.k8s.io kind: Role name: k8s-nim-operator-leader-election-role subjects: - kind: ServiceAccount name: k8s-nim-operator namespace: 'nvidia-nim' --- # Source: k8s-nim-operator/templates/admission-controller.yaml apiVersion: v1 kind: Service metadata: name: k8s-nim-operator-webhook-service namespace: nvidia-nim labels: control-plane: controller-manager app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator spec: ports: - port: 443 protocol: TCP targetPort: 9443 selector: control-plane: controller-manager app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator --- # Source: k8s-nim-operator/templates/metrics-service.yaml apiVersion: v1 kind: Service metadata: name: k8s-nim-operator-metrics-service labels: app.kubernetes.io/component: kube-rbac-proxy app.kubernetes.io/created-by: k8s-nim-operator app.kubernetes.io/part-of: k8s-nim-operator control-plane: controller-manager helm.sh/chart: k8s-nim-operator-3.1.0 app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator app.kubernetes.io/version: "3.1.0" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP selector: control-plane: controller-manager app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator ports: - name: metrics port: 8080 protocol: TCP --- # Source: k8s-nim-operator/templates/deployment.yaml apiVersion: apps/v1 kind: Deployment metadata: name: k8s-nim-operator labels: app.kubernetes.io/component: manager app.kubernetes.io/created-by: k8s-nim-operator app.kubernetes.io/part-of: k8s-nim-operator control-plane: controller-manager helm.sh/chart: k8s-nim-operator-3.1.0 app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator app.kubernetes.io/version: "3.1.0" app.kubernetes.io/managed-by: Helm annotations: {} spec: replicas: 1 selector: matchLabels: control-plane: controller-manager app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator template: metadata: labels: control-plane: controller-manager app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/instance: k8s-nim-operator annotations: kubectl.kubernetes.io/default-container: manager spec: containers: - args: - --health-probe-bind-address=:8081 - --metrics-bind-address=:8080 - --leader-elect - --zap-devel=false - --zap-log-level=info - --zap-stacktrace-level=error - --zap-encoder=json command: - /manager image: nvcr.io/nvidia/cloud-native/k8s-nim-operator:v3.1.0 imagePullPolicy: Always ports: - containerPort: 9443 name: webhook-server protocol: TCP volumeMounts: - mountPath: /tmp/k8s-webhook-server/serving-certs name: cert readOnly: true env: - name: WATCH_NAMESPACE value: "" - name: OPERATOR_NAMESPACE valueFrom: fieldRef: fieldPath: metadata.namespace - name: ENABLE_WEBHOOKS value: "true" livenessProbe: httpGet: path: /healthz port: 8081 initialDelaySeconds: 15 periodSeconds: 20 name: manager readinessProbe: httpGet: path: /readyz port: 8081 initialDelaySeconds: 5 periodSeconds: 10 resources: limits: cpu: "1" memory: 256Mi requests: cpu: 500m memory: 128Mi securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL imagePullSecrets: securityContext: runAsNonRoot: true seccompProfile: type: RuntimeDefault serviceAccountName: k8s-nim-operator terminationGracePeriodSeconds: 10 volumes: - name: cert secret: secretName: k8s-nim-operator-webhook-server-cert defaultMode: 420 affinity: nodeAffinity: preferredDuringSchedulingIgnoredDuringExecution: - preference: matchExpressions: - key: node-role.kubernetes.io/control-plane operator: In values: - "" weight: 1 tolerations: - operator: Exists --- # Source: k8s-nim-operator/templates/admission-controller.yaml apiVersion: admissionregistration.k8s.io/v1 kind: ValidatingWebhookConfiguration metadata: name: k8s-nim-operator-validating-webhook-configuration annotations: cert-manager.io/inject-ca-from: nvidia-nim/k8s-nim-operator-serving-cert labels: app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/managed-by: helm webhooks: - name: vnimcache-v1alpha1.kb.io admissionReviewVersions: ["v1"] clientConfig: service: name: k8s-nim-operator-webhook-service namespace: nvidia-nim path: /validate-apps-nvidia-com-v1alpha1-nimcache failurePolicy: Fail rules: - apiGroups: ["apps.nvidia.com"] apiVersions: ["v1alpha1"] operations: ["CREATE", "UPDATE"] resources: ["nimcaches"] sideEffects: None - name: vnimservice-v1alpha1.kb.io admissionReviewVersions: ["v1"] clientConfig: service: name: k8s-nim-operator-webhook-service namespace: nvidia-nim path: /validate-apps-nvidia-com-v1alpha1-nimservice failurePolicy: Fail rules: - apiGroups: ["apps.nvidia.com"] apiVersions: ["v1alpha1"] operations: ["CREATE", "UPDATE"] resources: ["nimservices"] sideEffects: None --- # Source: k8s-nim-operator/templates/admission-controller.yaml apiVersion: cert-manager.io/v1 kind: Certificate metadata: name: k8s-nim-operator-serving-cert namespace: nvidia-nim labels: app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/managed-by: helm spec: dnsNames: - k8s-nim-operator-webhook-service.nvidia-nim.svc - k8s-nim-operator-webhook-service.nvidia-nim.svc.cluster.local issuerRef: kind: Issuer name: k8s-nim-operator-selfsigned-issuer secretName: k8s-nim-operator-webhook-server-cert --- # Source: k8s-nim-operator/templates/admission-controller.yaml apiVersion: cert-manager.io/v1 kind: Issuer metadata: name: k8s-nim-operator-selfsigned-issuer namespace: nvidia-nim labels: app.kubernetes.io/name: k8s-nim-operator app.kubernetes.io/managed-by: helm spec: selfSigned: {}