Modal CI #29
This file contains hidden or 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: deepspeed-torch-latest-modal | |
| # This CI is running on modal.com's GPUs. | |
| # | |
| # It's set up here on github actions and then the cloned repo is sent to modal and everything | |
| # happens on their hw - see arctic_training/ci.py for where the actual vm is loaded, updated and the tests are | |
| # run. | |
| # | |
| # Both files are annotated to what's important and how one might change or update things if needed. | |
| # | |
| # Note that since this is a Required job we can't use `on.push.path` file filter - we are using | |
| # collect-tests job to do the filtering for us so that the job can be skipped and satisfy the | |
| # Required status for PRs to pass. | |
| # | |
| on: | |
| workflow_dispatch: | |
| push: | |
| branches: | |
| - master | |
| pull_request: | |
| types: [draft, opened, ready_for_review, synchronize] | |
| branches: | |
| - master | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref || github.run_id }} | |
| cancel-in-progress: true | |
| jobs: | |
| collect-tests: | |
| name: Collect tests to run | |
| runs-on: ubuntu-latest | |
| permissions: | |
| contents: read | |
| pull-requests: read | |
| outputs: | |
| deepspeed: ${{ steps.filter.outputs.deepspeed }} | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v4 | |
| with: | |
| lfs: true | |
| - name: Filter changed files | |
| uses: dorny/paths-filter@v2 | |
| id: filter | |
| with: | |
| token: ${{ secrets.GITHUB_TOKEN }} | |
| filters: | | |
| deepspeed: | |
| - 'deepspeed/**/*.py' | |
| - '.github/workflows/deepspeed.yml' | |
| deploy: | |
| name: DeepSpeedAI CI | |
| runs-on: ubuntu-latest | |
| needs: collect-tests | |
| env: | |
| # these are created at https://modal.com/settings/deepspeedai/tokens | |
| # they are then added to the repo's secrets at https://github.com/deepspeedai/deepspeed/settings/secrets/actions | |
| MODAL_TOKEN_ID: ${{ secrets.MODAL_TOKEN_ID }} | |
| MODAL_TOKEN_SECRET: ${{ secrets.MODAL_TOKEN_SECRET }} | |
| # this one comes from https://huggingface.co/settings/profile of the bot user | |
| # and it too is then updated at https://github.com/deepspeedai/deepspeed/settings/secrets/actions | |
| HF_TOKEN: ${{ secrets.HF_TOKEN }} | |
| if: needs.collect-tests.outputs.deepspeed == 'true' | |
| steps: | |
| - name: Checkout Repository | |
| uses: actions/checkout@v4 | |
| with: | |
| lfs: true | |
| - name: Install Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.10" | |
| cache: 'pip' # caching pip dependencies | |
| - name: Install build dependencies | |
| run: | | |
| pip install uv==0.4.0 # much faster than pip | |
| uv pip install --system modal | |
| uv pip install --system .[dev,1bit,autotuning,deepcompile] | |
| ds_report | |
| # time uv pip compile arctic_training/setup.py --extra all -o arctic_training/ci-requirements.txt | |
| # # add vllm manually to deps since it fails pip compile w/o CUDA_HOME being set in github actions | |
| # # if changing the version here also change it in setup.py to match | |
| # echo 'vllm==0.6.2' >> arctic_training/ci-requirements.txt | |
| - name: Run tests | |
| run: | | |
| modal run -m deepspeed.modal_ci.torch_latest |