add zero3 module_granularity_threshold to zero optimization.
#855
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: nv-ds-chat | |
| on: | |
| schedule: | |
| - cron: "0 0 * * *" | |
| workflow_dispatch: | |
| inputs: | |
| dse_branch: | |
| description: 'DeepSpeedExamples Branch' | |
| required: false | |
| default: 'master' | |
| type: string | |
| pull_request: | |
| paths: | |
| - ".github/workflows/nv-ds-chat.yml" | |
| - "deepspeed/runtime/zero/stage_1_and_2.py" | |
| - "deepspeed/runtime/zero/stage3.py" | |
| - "deepspeed/runtime/hybrid_engine.py" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| permissions: | |
| contents: read | |
| issues: write | |
| jobs: | |
| unit-tests: | |
| runs-on: [self-hosted, nvidia, cu121, v100] | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - id: setup-venv | |
| uses: ./.github/workflows/setup-venv | |
| - name: Install pytorch | |
| run: | | |
| pip3 install -U --cache-dir $TORCH_CACHE torch --index-url https://download.pytorch.org/whl/cu121 | |
| python -c "import torch; print('torch:', torch.__version__, torch)" | |
| python -c "import torch; print('CUDA available:', torch.cuda.is_available())" | |
| - name: Install deepspeed | |
| run: | | |
| pip install transformers==4.45.2 | |
| pip install .[dev] | |
| ds_report | |
| - name: Install deepspeed-chat | |
| run: | | |
| BRANCH="master" | |
| if [[ ! -z "${{ github.event.inputs.dse_branch }}" ]]; then | |
| BRANCH="${{ github.event.inputs.dse_branch }}" | |
| fi | |
| echo "DeepSpeedExamples Branch: $BRANCH" | |
| git clone -b $BRANCH https://github.com/microsoft/DeepSpeedExamples.git | |
| cd DeepSpeedExamples/applications/DeepSpeed-Chat | |
| pip install -r requirements.txt | |
| pip install -e . | |
| - name: Python environment | |
| run: | | |
| pip list | |
| - name: DS-Chat unit tests | |
| run: | | |
| cd DeepSpeedExamples/applications/DeepSpeed-Chat | |
| unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch | |
| cd tests | |
| pytest $PYTEST_OPTS ./ | |
| - name: Open GitHub issue if nightly CI fails | |
| if: ${{ failure() && (github.event_name == 'schedule') }} | |
| uses: JasonEtco/create-an-issue@v2 | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| with: | |
| filename: .github/ISSUE_TEMPLATE/ci_failure_report.md | |
| update_existing: true |