name: docker-multigpu-tests-biweekly

on:
  pull_request:
    paths:
      - 'tests/e2e/multigpu/**.py'
      - 'requirements.txt'
      - 'setup.py'
      - 'pyproject.toml'
      - '.github/workflows/multi-gpu-e2e.yml'
      - 'scripts/cutcrossentropy_install.py'
      - 'src/axolotl/core/trainers/mixins/sequence_parallel.py'
      - 'src/axolotl/utils/distributed.py'
  workflow_dispatch:
  schedule:
    - cron: '0 0 * * 1,4'  # Runs at 00:00 UTC every monday & thursday

# Cancel jobs on the same ref if a new one is triggered
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}

permissions:
  contents: read

env:
  MODAL_IMAGE_BUILDER_VERSION: "2025.06"

jobs:
  test-axolotl-multigpu:
    if: ${{ ! contains(github.event.commits[0].message, '[skip e2e]') && github.repository_owner == 'axolotl-ai-cloud' && (github.event_name != 'pull_request' || !github.event.pull_request.draft) }}
    strategy:
      fail-fast: false
      matrix:
        include:
#          - cuda: 129
#            cuda_version: 12.9.1
#            python_version: "3.12"
#            pytorch: 2.9.1
#            axolotl_extras: "fbgemm-gpu"
#            num_gpus: 2
#            dockerfile: "Dockerfile-uv.jinja"
          - cuda: 130
            cuda_version: 13.0.0
            python_version: "3.11"
            pytorch: 2.9.1
            axolotl_extras:
#            axolotl_extras: fbgemm-gpu
            num_gpus: 2
          - cuda: 128
            cuda_version: 12.8.1
            python_version: "3.11"
            pytorch: 2.10.0
            axolotl_extras: "fbgemm-gpu"
            num_gpus: 2
            dockerfile: "Dockerfile-uv.jinja"
    runs-on: [self-hosted, modal]
    timeout-minutes: 120
    steps:
      - name: Checkout
        uses: actions/checkout@v4
      - name: Install Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
      - name: Install Modal
        run: |
          python -m pip install --upgrade pip
          pip install modal==1.3.0.post1 jinja2
      - name: Update env vars
        run: |
          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
          echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
          echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
          echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile.jinja'}}" >> $GITHUB_ENV
      - name: Run tests job on Modal
        env:
          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
        run: |
          modal run -m cicd.multigpu