Repository navigation
refactor: organize models, backends, contracts and train and rollout engines #892
Workflow file for this run
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: GPU CI | ||
|
Check warning on line 1 in .github/workflows/gpu-ci.yml
|
||
| on: | ||
| pull_request_target: | ||
| branches: [ main, test ] | ||
| paths: | ||
| - 'csrc/**' | ||
| - 'rl_engine/**' | ||
| - 'tests/**' | ||
| - 'pyproject.toml' | ||
| - 'setup.py' | ||
| - 'requirements*.txt' | ||
| - 'requirements/**' | ||
| - 'build_tools/**' | ||
| - 'MANIFEST.in' | ||
| - 'docker/Dockerfile.cuda' | ||
| - 'ci/scripts/run_gpu_ci.sh' | ||
| - '.github/workflows/gpu-ci.yml' | ||
| types: [ opened, synchronize, reopened, labeled ] | ||
| concurrency: | ||
| group: gpu-ci-serial | ||
| cancel-in-progress: false | ||
| jobs: | ||
| gpu-tests: | ||
| if: contains(github.event.pull_request.labels.*.name, 'needs-gpu-ci') | ||
| runs-on: ubuntu-latest | ||
| timeout-minutes: 60 | ||
| strategy: | ||
| fail-fast: false | ||
| matrix: | ||
| include: | ||
| - { gpu_id: "NVIDIA RTX A4000", target_sm: "8.6" } # SM86 | ||
| - { gpu_id: "NVIDIA H100 80GB HBM3", target_sm: "9.0", force_sm90: "1" } # SM90 | ||
| steps: | ||
| - name: Checkout secure orchestrator script from base branch | ||
| uses: actions/checkout@v4 | ||
| with: | ||
| ref: ${{ github.event.pull_request.base.sha }} | ||
| - name: Install runpodctl | ||
| run: | | ||
| wget -qO runpodctl https://github.com/runpod/runpodctl/releases/latest/download/runpodctl-linux-amd64 | ||
| chmod +x runpodctl | ||
| sudo mv runpodctl /usr/local/bin/runpodctl | ||
| runpodctl version | ||
| - name: Configure runpodctl | ||
| run: runpodctl config --apiKey "${{ secrets.RUNPOD_API_KEY }}" | ||
| - name: Setup SSH key | ||
| run: | | ||
| mkdir -p ~/.ssh && chmod 700 ~/.ssh | ||
| printf '%s\n' "${{ secrets.RUNPOD_SSH_PRIVATE_KEY }}" > ~/.ssh/id_ed25519 | ||
| chmod 600 ~/.ssh/id_ed25519 | ||
| ssh-keygen -y -f ~/.ssh/id_ed25519 > /dev/null && echo "key OK" || echo "key BROKEN" | ||
| # Follow-up (#191): to test multiple architectures, add a matrix and pass | ||
| # GPU_ID + TARGET_SM (+ KERNEL_ALIGN_FORCE_SM90 for Hopper) through to the script. | ||
| # run_gpu_ci.sh reads all three, normalizes TARGET_SM, asserts the pod matches it, | ||
| # and forwards KERNEL_ALIGN_FORCE_SM90 into the remote build: | ||
| # strategy: | ||
| # matrix: | ||
| # include: | ||
| # - { gpu_id: "NVIDIA RTX A4000", target_sm: "8.6" } # Ampere | ||
| # - { gpu_id: "NVIDIA A100 80GB PCIe", target_sm: "8.0" } | ||
| # - { gpu_id: "NVIDIA H100 PCIe", target_sm: "9.0", force_sm90: "1" } # build Hopper TMA/WGMMA kernels | ||
| # - { gpu_id: "NVIDIA B200", target_sm: "10.0" } | ||
| # Per-arch jobs must NOT fall back to a different-capability GPU: the script | ||
| # fails fast when the pod arch != requested TARGET_SM, so keep fallback within | ||
| # the same compute capability (or unset it for these jobs). | ||
| - name: Run GPU tests on RunPod | ||
| env: | ||
| RUNPOD_API_KEY: ${{ secrets.RUNPOD_API_KEY }} | ||
| PR_REPO_URL: ${{ github.event.pull_request.head.repo.clone_url }} | ||
| PR_SHA: ${{ github.event.pull_request.head.sha }} | ||
| GPU_ID: ${{ matrix.gpu_id }} | ||
| TARGET_SM: ${{ matrix.target_sm }} | ||
| KERNEL_ALIGN_FORCE_SM90: ${{ matrix.force_sm90 }} | ||
| run: bash ci/scripts/run_gpu_ci.sh | ||
