Support sanity checking weight consistency especially for RL #8899
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: PR Test (XPU) | |
| on: | |
| push: | |
| branches: [ main ] | |
| pull_request: | |
| branches: [ main ] | |
| workflow_dispatch: | |
| concurrency: | |
| group: pr-test-xpu-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| # ==================== Check Changes ==================== # | |
| check-changes: | |
| runs-on: ubuntu-latest | |
| outputs: | |
| main_package: ${{ steps.filter.outputs.main_package }} | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v4 | |
| - name: Detect file changes | |
| id: filter | |
| uses: dorny/paths-filter@v3 | |
| with: | |
| filters: | | |
| main_package: | |
| - "python/sglang/!(multimodal_gen)/**" | |
| - "python/*.toml" | |
| - "scripts/ci/**" | |
| - "test/**" | |
| - "sgl-kernel/**" | |
| - ".github/workflows/pr-test-xpu.yml" | |
| - "docker/xpu.Dockerfile" | |
| # ==================== PR Gate ==================== # | |
| pr-gate: | |
| needs: check-changes | |
| if: needs.check-changes.outputs.main_package == 'true' | |
| uses: ./.github/workflows/pr-gate.yml | |
| secrets: inherit | |
| build-and-test: | |
| needs: [check-changes, pr-gate] | |
| if: needs.check-changes.outputs.main_package == 'true' | |
| runs-on: intel-bmg | |
| env: | |
| HF_HOME: /home/sdp/.cache/huggingface | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| - name: Set up Docker Buildx | |
| uses: docker/setup-buildx-action@v3 | |
| - name: Build Docker image | |
| run: | | |
| PR_REPO=${{ github.event.pull_request.head.repo.clone_url }} | |
| PR_HEAD_REF=${{ github.head_ref }} | |
| docker build \ | |
| ${PR_REPO:+--build-arg SG_LANG_REPO=$PR_REPO} \ | |
| ${PR_HEAD_REF:+--build-arg SG_LANG_BRANCH=$PR_HEAD_REF} \ | |
| --no-cache --progress=plain -f docker/xpu.Dockerfile -t xpu_sglang_main:bmg . | |
| - name: Run container | |
| id: start_container | |
| run: | | |
| container_id=$(docker run -dt \ | |
| --group-add 992 \ | |
| --group-add $(getent group video | cut -d: -f3) \ | |
| -v ${HF_HOME}:/root/.cache/huggingface \ | |
| --device /dev/dri \ | |
| -e HF_TOKEN="$(cat ~/huggingface_token.txt)" \ | |
| xpu_sglang_main:bmg) | |
| echo "Started container: $container_id" | |
| echo "container_id=$container_id" >> "$GITHUB_OUTPUT" | |
| - name: Install Dependency | |
| timeout-minutes: 20 | |
| run: | | |
| cid="${{ steps.start_container.outputs.container_id }}" | |
| docker exec "$cid" /home/sdp/miniforge3/envs/py3.10/bin/python3 -m pip install --upgrade pip | |
| docker exec "$cid" /home/sdp/miniforge3/envs/py3.10/bin/python3 -m pip install pytest expecttest ray huggingface_hub | |
| docker exec "$cid" /home/sdp/miniforge3/envs/py3.10/bin/python3 -m pip uninstall -y flashinfer-python | |
| docker exec "$cid" /bin/bash -c '/home/sdp/miniforge3/envs/py3.10/bin/huggingface-cli login --token ${HF_TOKEN} ' | |
| docker exec -u root "$cid" /bin/bash -c "ln -sf /home/sdp/miniforge3/envs/py3.10/bin/python3 /usr/bin/python3" | |
| - name: Run E2E Bfloat16 tests | |
| timeout-minutes: 20 | |
| run: | | |
| cid="${{ steps.start_container.outputs.container_id }}" | |
| docker exec -w /home/sdp/sglang/ "$cid" \ | |
| bash -c "LD_LIBRARY_PATH=/home/sdp/miniforge3/envs/py3.10/lib:$LD_LIBRARY_PATH && cd ./test/srt && python3 run_suite.py --suite per-commit-xpu" | |
| - name: Cleanup container | |
| if: always() | |
| run: | | |
| cid="${{ steps.start_container.outputs.container_id }}" | |
| docker rm -f "$cid" || true | |
| finish: | |
| if: always() | |
| needs: [build-and-test, pr-gate] | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Check job status | |
| run: | | |
| result="${{ needs.build-and-test.result }}" | |
| if [ "$result" != "success" ] && [ "$result" != "skipped" ]; then | |
| echo "Job failed with result: $result" | |
| exit 1 | |
| fi | |
| echo "All jobs completed successfully (result: $result)" | |
| exit 0 |