agentic-pd-hybrid/third_party/sglang/.github/workflows/pr-test-xpu.yml

name: PR Test (XPU)

on:
  push:
    branches: [ main ]
  pull_request:
    branches: [ main ]
  workflow_dispatch:
  workflow_call:
    inputs:
      ref:
        description: 'Git ref (branch, tag, or SHA) to test. If not provided, uses the default branch.'
        required: false
        type: string
        default: ''
      run_all_tests:
        description: "Run all tests (for releasing or testing purpose)"
        required: false
        type: boolean
        default: false

concurrency:
  group: pr-test-xpu-${{ inputs.ref || github.ref }}
  cancel-in-progress: ${{ github.event_name != 'workflow_call' }}

jobs:
  # ==================== Check Changes ==================== #
  check-changes:
    runs-on: ubuntu-latest
    outputs:
      main_package: ${{ steps.filter.outputs.main_package || steps.run-mode.outputs.run_all_tests }}
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          ref: ${{ inputs.ref || github.ref }}

      - name: Determine run mode
        id: run-mode
        run: |
          # Run all tests for workflow_call (when ref input is provided)
          # Note: github.event_name is inherited from caller, so we detect workflow_call by checking inputs.ref
          if [[ "${{ inputs.run_all_tests }}" == "true" ]]; then
            echo "run_all_tests=true" >> $GITHUB_OUTPUT
            echo "Run mode: ALL TESTS (run_all_tests=${{ inputs.run_all_tests }})"
          else
            echo "run_all_tests=false" >> $GITHUB_OUTPUT
            echo "Run mode: FILTERED (triggered by ${{ github.event_name }})"
          fi
      - name: Detect file changes
        id: filter
        uses: dorny/paths-filter@v3
        if: steps.run-mode.outputs.run_all_tests != 'true'
        with:
          filters: |
            main_package:
              - "python/sglang/!(multimodal_gen)/**/!(*.md)"
              - "python/pyproject_xpu.toml"
              - "test/**/!(*.md)"
              - "sgl-kernel/**/*.!(md|txt)"
              - ".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
          ref: ${{ inputs.ref || github.ref }}

      - 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/hf auth login --token ${HF_TOKEN} '


      - name: Run E2E Bfloat16 tests
        timeout-minutes: 20
        run: |
          cid="${{ steps.start_container.outputs.container_id }}"
          docker exec "$cid" bash -c "source /home/sdp/miniforge3/bin/activate && conda activate py3.10 && cd /home/sdp/sglang/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