nv-lightning-v100.yml

name: nv-lightning-v100

on:
  workflow_dispatch:
  pull_request:
    paths-ignore:
      - 'docs/**'
      - 'blogs/**'
      - 'deepspeed/inference/v2/**'
      - 'tests/unit/inference/v2/**'
  merge_group:
    branches: [ master ]
  schedule:
    - cron: "0 0 * * *"

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

jobs:
  unit-tests:
    runs-on: [self-hosted, nvidia, cu111, v100]

    env: {ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true} # Allow using Node16 actions

    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 torchvision --index-url https://download.pytorch.org/whl/cu118
          python -c "import torch; print('torch:', torch.__version__, torch)"
          python -c "import torch; print('CUDA available:', torch.cuda.is_available())"

      - name: Install deepspeed
        run: |
          pip install .[dev,autotuning]
          ds_report

      - name: Python environment
        run: |
          pip list

      - name: PyTorch Lightning Tests
        run: |
          unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
          pip install pytorch-lightning
          pip install "protobuf<4.21.0"
          cd tests
          pytest $PYTEST_OPTS lightning/