test_gpu_turnkey.yml

# This workflow will install Python dependencies, run tests and lint with a single version of Python
# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python

name: Test TurnkeyML on Azure GPUs

on:
  # Allows users to manually trigger the workflow using the GitHub UI
  workflow_dispatch:

permissions:
  contents: read

jobs:
  start_vm:
    timeout-minutes: 10
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - name: Install az cli
        run: |
          sudo apt-get update
          sudo apt-get install -y azure-cli
      - name: Turn on Azure VM
        run: |
          az login --username ${{ secrets.AZURE_CLIENT_ID }} --password ${{ secrets.AZURE_CLIENT_PWD }}
          az vm wait --name morecuda --resource-group morecuda_group --custom "instanceView.statuses[?code=='PowerState/deallocated']" --interval 30
          az vm start --name morecuda --resource-group morecuda_group
          az vm wait --created --name morecuda --resource-group morecuda_group
          az vm run-command invoke --name morecuda --resource-group morecuda_group --command-id RunShellScript --scripts 'export RUNNER_ALLOW_RUNASROOT="1" && export HOME="/home/azureuser" && bash /home/azureuser/actions-runner/run.sh &'
  build_and_test:
    needs: start_vm
    timeout-minutes: 10
    if: ${{ needs.start_vm.result == 'success' }}
    runs-on: self-hosted
    env:
      TURNKEY_VERBOSITY: static
      TURNKEY_TRACEBACK: True
    strategy:
      matrix:
        python-version: ["3.8"]
    steps:
      - uses: actions/checkout@v3
      - uses: conda-incubator/setup-miniconda@v3
        with:
          miniconda-version: "latest"
          activate-environment: tkml
          python-version: ${{ matrix.python-version }}
      - name: Install Docker
        shell: bash -el {0}
        run: |
          sudo mkdir -p /etc/apt/keyrings
          sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor --yes -o /etc/apt/keyrings/docker.gpg
          sudo chmod a+r /etc/apt/keyrings/docker.gpg
          echo \
          "deb [arch="$(dpkg --print-architecture)" signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu \
          "$(. /etc/os-release && echo "$VERSION_CODENAME")" stable" | \
          sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
          sudo apt-get update
          sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
          sudo chmod 666 /var/run/docker.sock
      - name: Install dependencies
        shell: bash -el {0}
        run: |
          python -m pip install --upgrade pip
          conda install pylint
          pip install -e .
          pip install transformers
          python -m pip check
      - name: Test with unittest
        shell: bash -el {0}
        run: |
          # E2E tests
          python test/gpu.py
  deallocate_vm:
    needs: build_and_test
    if: always()
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - name: Install az cli
        run: |
          sudo apt-get update
          sudo apt-get install -y azure-cli
      - name: Deallocate Azure VM
        run: |
          az login --username ${{ secrets.AZURE_CLIENT_ID }} --password ${{ secrets.AZURE_CLIENT_PWD }}
          az vm deallocate --name morecuda --resource-group morecuda_group