.github/workflows/tests.yml

name: Tests
on:
  # check on push/merge to main, PRs, and manual triggers
  push:
    branches:
      - "main"
    paths:
      - '**.py'
      - 'requirements.txt'
      - '.github/workflows/*.yml'
  pull_request:
      paths:
       - '**.py'
       - 'requirements.txt'
       - '.github/workflows/*.yml'
  workflow_dispatch:

jobs:
  pre-commit:
    name: pre-commit
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - uses: actions/setup-python@v4
        with:
          python-version: "3.9"
          cache: 'pip' # caching pip dependencies
      - uses: pre-commit/action@v3.0.0

  pytest:
    name: PyTest
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        python_version: ["3.9", "3.10", "3.11"]
    timeout-minutes: 10

    steps:
      - name: Check out repository code
        uses: actions/checkout@v3

      - name: Setup Python
        uses: actions/setup-python@v4
        with:
          python-version: ${{ matrix.python_version }}
          cache: 'pip' # caching pip dependencies

      - name: Install dependencies
        run: |
          pip3 install -U -e .
          pip3 install -r requirements-tests.txt

      - name: Run tests
        run: |
          pytest --ignore=tests/e2e/ tests/

  docker-e2e-tests:
    if: github.repository_owner == 'OpenAccess-AI-Collective'
    # this job needs to be run on self-hosted GPU runners...
    runs-on: [self-hosted, gpu, docker]
    timeout-minutes: 30
    needs: [pre-commit, pytest]

    strategy:
      fail-fast: false
      matrix:
        include:
          - cuda: 118
            cuda_version: 11.8.0
            python_version: "3.10"
            pytorch: 2.0.1
          - cuda: 121
            cuda_version: 12.1.0
            python_version: "3.10"
            pytorch: 2.1.2
    steps:
      - name: Checkout
        uses: actions/checkout@v4
      - name: Docker metadata
        id: metadata
        uses: docker/metadata-action@v5
        with:
          images: winglian/axolotl-tests
      - name: Build Docker image
        run: |
          # Set up build arguments
          BASE_TAG="main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}"
          CUDA="${{ matrix.cuda }}"
          PYTORCH_VERSION="${{ matrix.pytorch }}"
          # Build the Docker image
          docker build . \
            --file ./docker/Dockerfile-tests \
            --build-arg BASE_TAG=$BASE_TAG \
            --build-arg CUDA=$CUDA \
            --build-arg GITHUB_REF=$GITHUB_REF \
            --build-arg PYTORCH_VERSION=$PYTORCH_VERSION \
            --tag ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} \
            --no-cache
      - name: Unit Tests w docker image
        run: |
          docker run --rm ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} pytest --ignore=tests/e2e/ /workspace/axolotl/tests/
      - name: GPU Unit Tests w docker image
        run: |
          docker run --privileged --gpus "all" --env WANDB_DISABLED=true --rm ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} pytest --ignore=tests/e2e/patched/ /workspace/axolotl/tests/e2e/
      - name: GPU Unit Tests monkeypatched w docker image
        run: |
          docker run --privileged --gpus "all" --env WANDB_DISABLED=true --rm ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} pytest /workspace/axolotl/tests/e2e/patched/
      - name: Prune image from docker
        if: github.ref != 'refs/heads/main'
        run: |
          docker rmi -f ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}