apiVersion: batch/v1
kind: Job
metadata:
  name: test-tas-job
  namespace: hyperpod-ns-team-name
  labels:
    kueue.x-k8s.io/queue-name: hyperpod-ns-team-name-localqueue
    kueue.x-k8s.io/priority-class: PRIORITY_CLASS-priority
spec:
  parallelism: 10
  completions: 10
  suspend: true
  template:
    metadata:
      labels:
        kueue.x-k8s.io/queue-name: hyperpod-ns-team-name-localqueue
      annotations:
        kueue.x-k8s.io/podset-required-topology: "topology.k8s.aws/network-node-layer-3"
        or
        kueue.x-k8s.io/podset-preferred-topology: "topology.k8s.aws/network-node-layer-3"
    spec:
      nodeSelector:
        topology.k8s.aws/network-node-layer-3: TOPOLOGY_LABEL_VALUE
      containers:
        - name: dummy-job
          image: gcr.io/k8s-staging-perf-tests/sleep:v0.1.0
          args: ["3600s"]
          resources:
            requests:
              cpu: "100"
      restartPolicy: Never

hyp create hyp-pytorch-job \                                            
  --version 1.1 \
  --job-name sample-pytorch-job \
  --image 123456789012.dkr.ecr.us-west-2.amazonaws.com/ptjob:latest \
  --pull-policy "Always" \
  --tasks-per-node 1 \
  --max-retry 1 \
  --priority high-priority \
  --namespace hyperpod-ns-team-name \
  --queue-name hyperpod-ns-team-name-localqueue \
  --preferred-topology-label topology.k8s.aws/network-node-layer-1

apiVersion: kubeflow.org/v1
kind: PyTorchJob
metadata:
  annotations: {}
  labels:
    kueue.x-k8s.io/queue-name: hyperpod-ns-team-name-localqueue
  name: tas-test-pytorch-job
  namespace: hyperpod-ns-team-name
spec:
  pytorchReplicaSpecs:
    Master:
      replicas: 1
      restartPolicy: OnFailure
      template:
        metadata:
          labels:
            kueue.x-k8s.io/queue-name: hyperpod-ns-team-name-localqueue
        spec:
          containers:
          - command:
            - python3
            - /opt/pytorch-mnist/mnist.py
            - --epochs=1
            image: docker.io/kubeflowkatib/pytorch-mnist:v1beta1-45c5727
            imagePullPolicy: Always
            name: pytorch
    Worker:
      replicas: 10
      restartPolicy: OnFailure
      template:
        metadata:
          # annotations:
            # kueue.x-k8s.io/podset-required-topology: "topology.k8s.aws/network-node-layer-3"
          labels:
            kueue.x-k8s.io/queue-name: hyperpod-ns-team-name-localqueue
        spec:
          containers:
          - command:
            - python3
            - /opt/pytorch-mnist/mnist.py
            - --epochs=1
            image: docker.io/kubeflowkatib/pytorch-mnist:v1beta1-45c5727
            imagePullPolicy: Always
            name: pytorch
            resources:
              limits:
                cpu: 1
              requests:
                memory: 200Mi
                cpu: 1
          #nodeSelector:
          #  topology.k8s.aws/network-node-layer-3: xxxxxxxxxxx

Konsol Manajemen AWS