[Enhance] Enable exclude_frozen_parameters for DeepSpeedEngine._zero3_consolidated_16bit_state_dict
#2864
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: pr_stage_test | |
| on: | |
| pull_request: | |
| paths-ignore: | |
| - ".github/**.md" | |
| - "docker/**" | |
| - "docs/**" | |
| - "README.md" | |
| - "README_zh-CN.md" | |
| - "CONTRIBUTING.md" | |
| - "CONTRIBUTING_zh-CN.md" | |
| - ".pre-commit-config.yaml" | |
| - ".pre-commit-config-zh-cn.yaml" | |
| - "examples/**" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| build_cpu: | |
| runs-on: ubuntu-22.04 | |
| strategy: | |
| matrix: | |
| python-version: [3.7] | |
| include: | |
| - torch: 1.8.1 | |
| torchvision: 0.9.1 | |
| steps: | |
| - uses: actions/checkout@v3 | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Upgrade pip | |
| run: python -m pip install pip --upgrade | |
| - name: Upgrade wheel | |
| run: python -m pip install wheel --upgrade | |
| - name: Install PyTorch | |
| run: pip install torch==${{matrix.torch}}+cpu torchvision==${{matrix.torchvision}}+cpu -f https://download.pytorch.org/whl/cpu/torch_stable.html | |
| - name: Build MMEngine from source | |
| run: pip install -e . -v | |
| - name: Install unit tests dependencies | |
| run: | | |
| pip install -r requirements/tests.txt | |
| pip install openmim | |
| mim install mmcv | |
| - name: Run unittests and generate coverage report | |
| run: | | |
| coverage run --branch --source mmengine -m pytest tests/ --ignore tests/test_dist | |
| coverage xml | |
| coverage report -m | |
| # Upload coverage report for python3.7 && pytorch1.8.1 cpu | |
| - name: Upload coverage to Codecov | |
| uses: codecov/codecov-action@v3 | |
| with: | |
| file: ./coverage.xml | |
| flags: unittests | |
| env_vars: OS,PYTHON | |
| name: codecov-umbrella | |
| fail_ci_if_error: false | |
| build_cu102: | |
| runs-on: ubuntu-22.04 | |
| container: | |
| image: pytorch/pytorch:1.8.1-cuda10.2-cudnn7-devel | |
| env: | |
| MKL_THREADING_LAYER: GNU | |
| strategy: | |
| matrix: | |
| python-version: [3.7] | |
| steps: | |
| - uses: actions/checkout@v3 | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Upgrade pip | |
| run: pip install pip --upgrade | |
| - name: Fetch GPG keys | |
| run: | | |
| apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub | |
| apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub | |
| - name: Install system dependencies | |
| run: apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libsm6 libxrender-dev libxext6 | |
| - name: Build MMEngine from source | |
| run: pip install -e . -v | |
| - name: Install unit tests dependencies | |
| run: | | |
| pip install -r requirements/tests.txt | |
| pip install openmim | |
| mim install mmcv | |
| - name: Run unittests and generate coverage report | |
| run: | | |
| coverage run --branch --source mmengine -m pytest tests/ --ignore tests/test_dist | |
| coverage xml | |
| coverage report -m | |
| build_cu117: | |
| runs-on: ubuntu-22.04 | |
| container: | |
| image: pytorch/pytorch:2.0.0-cuda11.7-cudnn8-devel | |
| strategy: | |
| matrix: | |
| python-version: [3.9] | |
| steps: | |
| - uses: actions/checkout@v3 | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Upgrade pip | |
| run: pip install pip --upgrade | |
| - name: Fetch GPG keys | |
| run: | | |
| apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub | |
| apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub | |
| - name: Install system dependencies | |
| run: apt-get update && apt-get install -y git ffmpeg libturbojpeg | |
| - name: Build MMEngine from source | |
| run: pip install -e . -v | |
| - name: Install unit tests dependencies | |
| run: | | |
| pip install -r requirements/tests.txt | |
| pip install openmim | |
| mim install mmcv | |
| # Distributed related unit test may randomly error in PyTorch 1.13.0 | |
| - name: Run unittests and generate coverage report | |
| run: | | |
| coverage run --branch --source mmengine -m pytest tests/ --ignore tests/test_dist/ | |
| coverage xml | |
| coverage report -m | |
| build_windows: | |
| runs-on: windows-2022 | |
| strategy: | |
| matrix: | |
| python-version: [3.7] | |
| platform: [cpu, cu111] | |
| torch: [1.8.1] | |
| torchvision: [0.9.1] | |
| include: | |
| - python-version: 3.8 | |
| platform: cu118 | |
| torch: 2.1.0 | |
| torchvision: 0.16.0 | |
| steps: | |
| - uses: actions/checkout@v3 | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Upgrade pip | |
| # Windows CI could fail If we call `pip install pip --upgrade` directly. | |
| run: python -m pip install pip --upgrade | |
| - name: Install PyTorch | |
| run: pip install torch==${{matrix.torch}}+${{matrix.platform}} torchvision==${{matrix.torchvision}}+${{matrix.platform}} -f https://download.pytorch.org/whl/${{matrix.platform}}/torch_stable.html | |
| - name: Build MMEngine from source | |
| run: pip install -e . -v | |
| - name: Install unit tests dependencies | |
| run: | | |
| pip install -r requirements/tests.txt | |
| pip install openmim | |
| mim install mmcv | |
| - name: Run CPU unittests | |
| run: pytest tests/ --ignore tests/test_dist | |
| if: ${{ matrix.platform == 'cpu' }} | |
| - name: Run GPU unittests | |
| # Skip testing distributed related unit tests since the memory of windows CI is limited | |
| run: pytest tests/ --ignore tests/test_dist --ignore tests/test_optim/test_optimizer/test_optimizer_wrapper.py --ignore tests/test_model/test_wrappers/test_model_wrapper.py --ignore tests/test_hooks/test_sync_buffers_hook.py | |
| if: ${{ matrix.platform == 'cu111' }} || ${{ matrix.platform == 'cu118' }} |