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' 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' }} jobs: test-axolotl-multigpu: if: ${{ ! contains(github.event.commits[0].message, '[skip e2e]') && github.repository_owner == 'axolotl-ai-cloud' }} strategy: fail-fast: false matrix: include: - cuda: 124 cuda_version: 12.4.1 python_version: "3.11" pytorch: 2.4.1 axolotl_extras: # no vllm support for 2.4.1 num_gpus: 2 nightly_build: "true" - cuda: 124 cuda_version: 12.4.1 python_version: "3.11" pytorch: 2.5.1 axolotl_extras: vllm num_gpus: 2 nightly_build: "true" - cuda: 124 cuda_version: 12.4.1 python_version: "3.11" pytorch: 2.6.0 # awaiting vllm#12721 axolotl_extras: num_gpus: 2 nightly_build: "true" runs-on: [self-hosted, modal] timeout-minutes: 120 steps: - name: Checkout uses: actions/checkout@v4 - name: Install Python uses: actions/setup-python@v5 with: python-version: "3.11" - name: Install Modal run: | python -m pip install --upgrade pip pip install modal==0.71.8 jinja2 - name: Update env vars run: | echo "BASE_TAG=main-base-py${{ 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 }}" >> $GITHUB_ENV echo "NIGHTLY_BUILD=${{ matrix.nightly_build }}" >> $GITHUB_ENV - name: Run tests job on Modal run: | modal run cicd.multigpu