test.yml

name: Step 4 - Test GPU Operator Installation

on:
  workflow_dispatch:

env:
  RESOURCE_GROUP: rg-pvt-aks-h100
  CLUSTER_NAME: pvt-aks-h100

jobs:
  test-gpu-operator:
    runs-on: ubuntu-latest

    permissions:
      id-token: write
      contents: read

    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Log in to Azure with federated identity (User Assigned Managed Identity)
        uses: azure/login@v2
        with:
          client-id: ${{ secrets.AZURE_CLIENT_ID }}
          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}

      - name: Apply pod-check-nvidia-smi.yml and check logs
        run: |
          az aks command invoke \
            --resource-group $RESOURCE_GROUP \
            --name $CLUSTER_NAME \
            --command "kubectl apply -f pod-check-nvidia-smi.yml -n default && kubectl wait --for=condition=Succeeded pod/nvidia-gpu-test -n default --timeout=120s" \
            --file pod-check-nvidia-smi.yml
          az aks command invoke \
            --resource-group $RESOURCE_GROUP \
            --name $CLUSTER_NAME \
            --command "kubectl logs nvidia-gpu-test -n default"