amd-mi200.yml

name: amd-mi200

on:
  workflow_dispatch:
  pull_request:
    paths:
      - '.github/workflows/amd-mi200.yml'
      - 'requirements/**'
  schedule:
    - cron: "0 0 * * *"

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read
  issues: write

jobs:
  amd-tests:
    # The type of runner that the job will run on
    runs-on: [self-hosted, amd, mi200]

    # Steps represent a sequence of tasks that will be executed as part of the job
    steps:
      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
      - uses: actions/checkout@v4

      - id: setup-venv
        uses: ./.github/workflows/setup-venv

      - name: Install pytorch
        run: |
          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/rocm6.0
          python -c "import torch; print('torch:', torch.__version__, torch)"
          python -c "import torch; print('CUDA available:', torch.cuda.is_available())"

      - name: Install transformers
        run: |
          git clone https://github.com/huggingface/transformers
          cd transformers
          # if needed switch to the last known good SHA until transformers@master is fixed
          # git checkout 1cc453d33
          git rev-parse --short HEAD
          pip install .

      - name: Install (ROCm) apex
        run: |
          git clone https://github.com/ROCmSoftwarePlatform/apex.git
          cd apex
          git checkout torch_2.1_higher
          CURRENT_VER=$(git rev-parse HEAD)
          INSTALLED_VER=$(cat /blob/amd-apex/.venv_installed_version)
          if [[ "$CURRENT_VER" != "$INSTALLED_VER" ]]; then
            pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings="--global-option=--cpp_ext" --config-settings="--global-option=--cuda_ext" --target=/blob/amd-apex/ --upgrade .
            git rev-parse HEAD > /blob/amd-apex/.venv_installed_version
          fi
          echo PYTHONPATH=$PYTHONPATH:/blob/amd-apex/ >> $GITHUB_ENV
      # Runs a set of commands using the runners shell
      - name: Install deepspeed
        run: |
          pip install .[dev,1bit,autotuning]
          #python -c "from deepspeed.env_report import cli_main; cli_main()"
          ds_report

      - name: Python environment
        run: |
          pip list

      # Runs a set of commands using the runners shell
      - name: Unit tests
        run: |
          unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
          cd tests
          pytest $PYTEST_OPTS -n 4 --verbose unit/
          pytest $PYTEST_OPTS -m 'sequential' unit/

      - name: Open GitHub issue if nightly CI fails
        if: ${{ failure() && (github.event_name == 'schedule') }}
        uses: JasonEtco/create-an-issue@v2
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        with:
          filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
          update_existing: true