nv-nightly.yml

name: nv-nightly

on:
  pull_request:
    branches:
      '**'
  schedule:
    - cron: "0 0 * * *"

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

permissions:
    contents: read
    issues: write

jobs:
  unit-tests:
    runs-on: [self-hosted, nvidia, cu116, v100]

    steps:
      - uses: actions/checkout@v3

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

      - name: Install pytorch
        run: |
          pip install -U --cache-dir $TORCH_CACHE torch==1.13.1 torchvision --extra-index-url https://download.pytorch.org/whl/cu116
          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 deepspeed
        run: |
          pip install .[dev,1bit,autotuning,inf]
          ds_report

      - name: Python environment
        run: |
          pip list

      - name: Unit tests
        run: |
          unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
          cd tests
          pytest $PYTEST_OPTS --forked -m 'nightly' unit/ --torch_ver="1.13" --cuda_ver="11.6"

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