(3/n) Support 2D Parallelism - Efficient loading of full-state checkpoints #8712
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Test Fabric | |
| # see: https://help.github.com/en/actions/reference/events-that-trigger-workflows | |
| on: | |
| push: | |
| branches: [master, "release/*"] | |
| pull_request: | |
| branches: [master, "release/*"] | |
| types: [opened, reopened, ready_for_review, synchronize] # added `ready_for_review` since draft is skipped | |
| paths: | |
| - ".actions/*" | |
| - "requirements/ci.txt" | |
| - "requirements/fabric/**" | |
| - "src/lightning/fabric/**" | |
| - "src/lightning_fabric/*" | |
| - "tests/tests_fabric/**" | |
| - "pyproject.toml" # includes pytest config | |
| - ".github/workflows/ci-tests-fabric.yml" | |
| - "!requirements/*/docs.txt" | |
| - "!*.md" | |
| - "!**/*.md" | |
| schedule: | |
| # At the end of every day | |
| - cron: "0 0 * * *" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref }} | |
| cancel-in-progress: ${{ github.event_name == 'pull_request' }} | |
| defaults: | |
| run: | |
| shell: bash | |
| jobs: | |
| fabric-cpu: | |
| runs-on: ${{ matrix.os }} | |
| if: github.event.pull_request.draft == false | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| include: | |
| - { os: "macOS-11", pkg-name: "lightning", python-version: "3.10", pytorch-version: "2.0" } | |
| - { os: "ubuntu-20.04", pkg-name: "lightning", python-version: "3.10", pytorch-version: "2.0" } | |
| - { os: "windows-2022", pkg-name: "lightning", python-version: "3.10", pytorch-version: "2.0" } | |
| # only run PyTorch latest | |
| - { os: "macOS-11", pkg-name: "lightning", python-version: "3.11", pytorch-version: "2.1" } | |
| - { os: "ubuntu-20.04", pkg-name: "lightning", python-version: "3.11", pytorch-version: "2.1" } | |
| - { os: "windows-2022", pkg-name: "lightning", python-version: "3.11", pytorch-version: "2.1" } | |
| - { os: "macOS-11", pkg-name: "lightning", python-version: "3.11", pytorch-version: "2.2" } | |
| - { os: "ubuntu-20.04", pkg-name: "lightning", python-version: "3.11", pytorch-version: "2.2" } | |
| - { os: "windows-2022", pkg-name: "lightning", python-version: "3.11", pytorch-version: "2.2" } | |
| - { os: "macOS-14", pkg-name: "lightning", python-version: "3.10", pytorch-version: "2.3" } | |
| - { os: "ubuntu-20.04", pkg-name: "lightning", python-version: "3.11", pytorch-version: "2.3" } | |
| - { os: "windows-2022", pkg-name: "lightning", python-version: "3.11", pytorch-version: "2.3" } | |
| # only run PyTorch latest with Python latest, use Fabric scope to limit dependency issues | |
| - { os: "macOS-12", pkg-name: "fabric", python-version: "3.11", pytorch-version: "2.0" } | |
| - { os: "ubuntu-22.04", pkg-name: "fabric", python-version: "3.11", pytorch-version: "2.0" } | |
| - { os: "windows-2022", pkg-name: "fabric", python-version: "3.11", pytorch-version: "2.0" } | |
| - { os: "macOS-12", pkg-name: "fabric", python-version: "3.11", pytorch-version: "2.1" } | |
| - { os: "ubuntu-22.04", pkg-name: "fabric", python-version: "3.11", pytorch-version: "2.1" } | |
| - { os: "windows-2022", pkg-name: "fabric", python-version: "3.11", pytorch-version: "2.1" } | |
| # "oldest" versions tests, only on minimum Python | |
| - { os: "macOS-11", pkg-name: "lightning", python-version: "3.8", pytorch-version: "2.0", requires: "oldest" } | |
| - { | |
| os: "ubuntu-20.04", | |
| pkg-name: "lightning", | |
| python-version: "3.8", | |
| pytorch-version: "2.0", | |
| requires: "oldest", | |
| } | |
| - { | |
| os: "windows-2022", | |
| pkg-name: "lightning", | |
| python-version: "3.8", | |
| pytorch-version: "2.0", | |
| requires: "oldest", | |
| } | |
| # "fabric" installs the standalone package | |
| - { os: "macOS-11", pkg-name: "fabric", python-version: "3.8", pytorch-version: "2.0" } | |
| - { os: "ubuntu-20.04", pkg-name: "fabric", python-version: "3.8", pytorch-version: "2.0" } | |
| - { os: "windows-2022", pkg-name: "fabric", python-version: "3.8", pytorch-version: "2.0" } | |
| timeout-minutes: 25 # because of building grpcio on Mac | |
| env: | |
| PACKAGE_NAME: ${{ matrix.pkg-name }} | |
| FREEZE_REQUIREMENTS: ${{ ! (github.ref == 'refs/heads/master' || startsWith(github.ref, 'refs/heads/release/')) }} | |
| PYPI_CACHE_DIR: "_pip-wheels" | |
| TORCH_URL_STABLE: "https://download.pytorch.org/whl/cpu/torch_stable.html" | |
| TORCH_URL_TEST: "https://download.pytorch.org/whl/test/cpu/torch_test.html" | |
| # TODO: Remove this - Enable running MPS tests on this platform | |
| DISABLE_MPS: ${{ matrix.os == 'macOS-14' && '1' || '0' }} | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: basic setup | |
| run: pip install -q -r .actions/requirements.txt | |
| - name: Set min. dependencies | |
| if: ${{ matrix.requires == 'oldest' }} | |
| run: python .actions/assistant.py replace_oldest_ver | |
| - name: Adjust PyTorch versions in requirements files | |
| if: ${{ matrix.requires != 'oldest' }} | |
| run: | | |
| pip install -q -r requirements/ci.txt | |
| python -m wget https://raw.githubusercontent.com/Lightning-AI/utilities/main/scripts/adjust-torch-versions.py | |
| for fpath in `ls requirements/**/*.txt`; do \ | |
| python ./adjust-torch-versions.py $fpath ${{ matrix.pytorch-version }}; \ | |
| done | |
| - name: pip wheels cache | |
| uses: actions/cache/restore@v4 | |
| with: | |
| path: ${{ env.PYPI_CACHE_DIR }} | |
| key: pypi_wheels | |
| - run: | | |
| mkdir -p $PYPI_CACHE_DIR | |
| ls -lh $PYPI_CACHE_DIR | |
| - name: Env. variables | |
| run: | | |
| # Switch PyTorch URL | |
| python -c "print('TORCH_URL=' + str('${{env.TORCH_URL_TEST}}' if '${{ matrix.pytorch-version }}' == '2.3' else '${{env.TORCH_URL_STABLE}}'))" >> $GITHUB_ENV | |
| # Switch coverage scope | |
| python -c "print('COVERAGE_SCOPE=' + str('lightning' if '${{matrix.pkg-name}}' == 'lightning' else 'lightning_fabric'))" >> $GITHUB_ENV | |
| # if you install mono-package set dependency only for this subpackage | |
| python -c "print('EXTRA_PREFIX=' + str('' if '${{matrix.pkg-name}}' != 'lightning' else 'fabric-'))" >> $GITHUB_ENV | |
| - name: Install package & dependencies | |
| timeout-minutes: 20 | |
| run: | | |
| pip install -e ".[${EXTRA_PREFIX}test,${EXTRA_PREFIX}strategies]" -U --prefer-binary \ | |
| --find-links="${TORCH_URL}" --find-links="${PYPI_CACHE_DIR}" | |
| pip list | |
| - name: Dump handy wheels | |
| if: github.event_name == 'push' && github.ref == 'refs/heads/master' | |
| continue-on-error: true | |
| uses: ./.github/actions/pip-wheels | |
| with: | |
| wheel-dir: ${{ env.PYPI_CACHE_DIR }} | |
| torch-url: ${{ env.TORCH_URL }} | |
| cache-key: "pypi_wheels" | |
| - name: Adjust tests | |
| if: ${{ matrix.pkg-name != 'lightning' }} | |
| run: | | |
| python .actions/assistant.py copy_replace_imports --source_dir="./tests" \ | |
| --source_import="lightning.fabric" --target_import="lightning_fabric" | |
| - name: Testing Warnings | |
| working-directory: tests/tests_fabric | |
| # needs to run outside `pytest` | |
| run: python utilities/test_warnings.py | |
| - name: Testing Fabric | |
| working-directory: tests/tests_fabric | |
| # NOTE: do not include coverage report here, see: https://github.com/nedbat/coveragepy/issues/1003 | |
| run: | | |
| echo $GITHUB_RUN_ID | |
| python -m coverage run --source ${{ env.COVERAGE_SCOPE }} \ | |
| -m pytest -v --timeout=30 --durations=50 --random-order-seed=$GITHUB_RUN_ID | |
| - name: Statistics | |
| if: success() | |
| working-directory: tests/tests_fabric | |
| run: | | |
| coverage report | |
| coverage xml | |
| - name: Upload coverage to Codecov | |
| uses: codecov/codecov-action@v4 | |
| # see: https://github.com/actions/toolkit/issues/399 | |
| continue-on-error: true | |
| with: | |
| token: ${{ secrets.CODECOV_TOKEN }} | |
| file: tests/tests_fabric/coverage.xml | |
| flags: ${{ env.COVERAGE_SCOPE }},cpu,pytest,python${{ matrix.python-version }} | |
| name: CPU-coverage | |
| fail_ci_if_error: false |