---
# Source: nvidia-device-plugin/templates/service-account.yml
apiVersion: v1
kind: ServiceAccount
metadata:
  name: nvidia-device-plugin-service-account
  namespace: gpu-operator
  labels:
    helm.sh/chart: nvidia-device-plugin-0.19.3
    app.kubernetes.io/name: nvidia-device-plugin
    app.kubernetes.io/instance: nvidia-device-plugin
    app.kubernetes.io/version: "0.19.3"
    app.kubernetes.io/managed-by: Helm
---
# Source: nvidia-device-plugin/templates/role.yml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: nvidia-device-plugin-role
  labels:
    helm.sh/chart: nvidia-device-plugin-0.19.3
    app.kubernetes.io/name: nvidia-device-plugin
    app.kubernetes.io/instance: nvidia-device-plugin
    app.kubernetes.io/version: "0.19.3"
    app.kubernetes.io/managed-by: Helm
rules:
  - apiGroups: [""]
    resources: ["nodes"]
    verbs: ["get", "list", "watch"]
---
# Source: nvidia-device-plugin/templates/role-binding.yml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: nvidia-device-plugin-role-binding
  labels:
    helm.sh/chart: nvidia-device-plugin-0.19.3
    app.kubernetes.io/name: nvidia-device-plugin
    app.kubernetes.io/instance: nvidia-device-plugin
    app.kubernetes.io/version: "0.19.3"
    app.kubernetes.io/managed-by: Helm
subjects:
  - kind: ServiceAccount
    name: nvidia-device-plugin-service-account
    namespace: gpu-operator
roleRef:
  kind: ClusterRole
  name: nvidia-device-plugin-role
  apiGroup: rbac.authorization.k8s.io
---
# Source: nvidia-device-plugin/templates/daemonset-device-plugin.yml
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: nvidia-device-plugin
  namespace: gpu-operator
  labels:
    helm.sh/chart: nvidia-device-plugin-0.19.3
    app.kubernetes.io/name: nvidia-device-plugin
    app.kubernetes.io/instance: nvidia-device-plugin
    app.kubernetes.io/version: "0.19.3"
    app.kubernetes.io/managed-by: Helm
spec:
  selector:
    matchLabels:
      app.kubernetes.io/name: nvidia-device-plugin
      app.kubernetes.io/instance: nvidia-device-plugin
  updateStrategy:
    type: RollingUpdate
  template:
    metadata:
      labels:
        app.kubernetes.io/name: nvidia-device-plugin
        app.kubernetes.io/instance: nvidia-device-plugin
      annotations:
        {}
    spec:
      priorityClassName: system-node-critical
      securityContext:
        {}
      serviceAccountName: nvidia-device-plugin-service-account
      containers:
      - image: nvcr.io/nvidia/k8s-device-plugin:v0.19.3
        imagePullPolicy: IfNotPresent
        name: nvidia-device-plugin-ctr
        command: ["nvidia-device-plugin"]
        env:
          - name: MPS_ROOT
            value: /run/nvidia/mps
          - name: FAIL_ON_INIT_ERROR
            value: "true"
          - name: NVIDIA_VISIBLE_DEVICES
            value: all
          - name: NVIDIA_DRIVER_CAPABILITIES
            value: compute,utility
        securityContext:
          allowPrivilegeEscalation: false
          capabilities:
            drop: ["ALL"]
        volumeMounts:
          - name: kubelet-device-plugins-dir
            mountPath: /var/lib/kubelet/device-plugins
          # The MPS /dev/shm is needed to allow for MPS daemon health-checking.
          - name: mps-shm
            mountPath: /dev/shm
          - name: mps-root
            mountPath: /mps
          - name: cdi-root
            mountPath: /var/run/cdi
      volumes:
        - name: kubelet-device-plugins-dir
          hostPath:
            path: /var/lib/kubelet/device-plugins
            type: Directory
        - name: mps-root
          hostPath:
            path: /run/nvidia/mps
            type: DirectoryOrCreate
        - name: mps-shm
          hostPath:
            path: /run/nvidia/mps/shm
        - name: cdi-root
          hostPath:
            path: /var/run/cdi
            type: DirectoryOrCreate
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
            - matchExpressions:
              - key: eks-inference.confighub.com/accelerator
                operator: Exists
      tolerations:
        - effect: NoSchedule
          key: nvidia.com/gpu
          operator: Exists
        - effect: NoSchedule
          key: eks-inference.confighub.com/h200
          operator: Exists
---
# Source: nvidia-device-plugin/templates/daemonset-mps-control-daemon.yml
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: nvidia-device-plugin-mps-control-daemon
  namespace: gpu-operator
  labels:
    helm.sh/chart: nvidia-device-plugin-0.19.3
    app.kubernetes.io/name: nvidia-device-plugin
    app.kubernetes.io/instance: nvidia-device-plugin
    app.kubernetes.io/version: "0.19.3"
    app.kubernetes.io/managed-by: Helm
spec:
  selector:
    matchLabels:
      app.kubernetes.io/name: nvidia-device-plugin
      app.kubernetes.io/instance: nvidia-device-plugin
  updateStrategy:
    type: RollingUpdate
  template:
    metadata:
      labels:
        app.kubernetes.io/name: nvidia-device-plugin
        app.kubernetes.io/instance: nvidia-device-plugin
      annotations:
        {}
    spec:
      priorityClassName: system-node-critical
      securityContext:
        {}
      serviceAccountName: nvidia-device-plugin-service-account
      hostPID: true
      initContainers:
      - image: nvcr.io/nvidia/k8s-device-plugin:v0.19.3
        name: mps-control-daemon-mounts
        command: [mps-control-daemon, mount-shm]
        securityContext:
          privileged: true
        volumeMounts:
        - name: mps-root
          mountPath: /mps
          mountPropagation: Bidirectional
      containers:
        - image: nvcr.io/nvidia/k8s-device-plugin:v0.19.3
          imagePullPolicy: IfNotPresent
          name: mps-control-daemon-ctr
          command: [mps-control-daemon]
          env:
          - name: NODE_NAME
            valueFrom:
              fieldRef:
                apiVersion: v1
                fieldPath: spec.nodeName
          - name: NVIDIA_VISIBLE_DEVICES
            value: all
          - name: NVIDIA_DRIVER_CAPABILITIES
            value: compute,utility
          securityContext:
            privileged: true
          volumeMounts:
          - name: mps-shm
            mountPath: /dev/shm
          - name: mps-root
            mountPath: /mps
      volumes:
      - name: mps-root
        hostPath:
          path: /run/nvidia/mps
          type: DirectoryOrCreate
      - name: mps-shm
        hostPath:
          path: /run/nvidia/mps/shm
      nodeSelector:
        # We only deploy this pod if the following sharing label is applied.
        nvidia.com/mps.capable: "true"
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
            - matchExpressions:
              - key: eks-inference.confighub.com/accelerator
                operator: Exists
      tolerations:
        - effect: NoSchedule
          key: nvidia.com/gpu
          operator: Exists
        - effect: NoSchedule
          key: eks-inference.confighub.com/h200
          operator: Exists
---
# Source: nvidia-device-plugin/templates/daemonset-device-plugin.yml
# Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
---
# Source: nvidia-device-plugin/templates/daemonset-gfd.yml
# Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
---
# Source: nvidia-device-plugin/templates/daemonset-mps-control-daemon.yml
# Copyright 2024 NVIDIA CORPORATION
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.