apiVersion: "trainer.kubeflow.org/v1alpha1"
kind: "ClusterTrainingRuntime"
metadata:
  annotations:
    {}
  labels:
    trainer.kubeflow.org/framework: "torch"
  name: "torch-distributed"
spec:
  mlPolicy:
    numNodes: 8
    torch:
      {}
  template:
    spec:
      replicatedJobs:
        -
          name: "node"
          template:
            metadata:
              labels:
                trainer.kubeflow.org/trainjob-ancestor-step: "trainer"
            spec:
              template:
                spec:
                  containers:
                    -
                      image: "pytorch/pytorch:latest"
                      name: "node"
                      env:
                        -
                          name: "AI_API_KEY"
                          value: "confighubplaceholder"
                  nodeSelector:
                    nvidia.com/gpu.present: "true"
                  tolerations:
                    -
                      operator: "Exists"