name: amd-mi100

on:
  schedule:
    - cron: "0 0 * * *"

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

jobs:
  amd-tests:
    # The type of runner that the job will run on
    runs-on: [self-hosted, amd, mi100]

    # 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@v3

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

      - name: Install pytorch
        run: |
          pip install --cache-dir $TORCH_CACHE torch==1.13.1 torchvision --extra-index-url https://download.pytorch.org/whl/rocm5.1.1
          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 .

      # 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/