sgl-project--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|THIRDPARTYNOTICES.txt|LICENSE)"
              - ".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

  # ==================== Stage A ==================== #
  stage-a-test-1-gpu-xpu:
    needs: [check-changes, pr-gate]
    if: needs.check-changes.outputs.main_package == 'true'
    runs-on: intel-bmg
    env:
      DOCKERHUB_INTEL_USERNAME: ${{ secrets.DOCKERHUB_INTEL_USERNAME }}
      DOCKERHUB_INTEL_TOKEN: ${{ secrets.DOCKERHUB_INTEL_TOKEN }}
    steps:
      - name: Reset workspace ownership
        run: |
          # Prior runs install sglang as root inside the CI container against
          # the bind-mounted workspace, leaving root-owned egg-info on the host.
          # actions/checkout's pre-clean step can't unlink those as the runner
          # user, so reset ownership before checkout runs.
          docker run --rm -v "${{ github.workspace }}:/w" busybox:latest \
            chown -R "$(id -u):$(id -g)" /w || true

      - name: Checkout code
        uses: actions/checkout@v4
        with:
          fetch-depth: 0
          ref: ${{ inputs.ref || github.ref }}

      - name: Start CI container
        run: |
          export HF_TOKEN="$(cat ~/huggingface_token.txt)"
          bash scripts/ci/xpu/xpu_ci_start_container.sh
        env:
          GITHUB_WORKSPACE: ${{ github.workspace }}

      - name: Install Dependency
        timeout-minutes: 60
        run: |
          docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install --upgrade pip
          docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install pytest expecttest ray huggingface_hub tabulate
          docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip uninstall -y flashinfer-python sgl-kernel sglang
          docker exec ci_sglang_xpu cp /sglang-checkout/python/pyproject_xpu.toml /sglang-checkout/python/pyproject.toml
          docker exec -w /sglang-checkout/python ci_sglang_xpu /opt/venv/bin/python3 -m pip install --no-cache-dir . --extra-index-url https://download.pytorch.org/whl/xpu
          docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install --no-cache-dir --no-deps xgrammar==0.1.33
          docker exec ci_sglang_xpu /bin/bash -c '/opt/venv/bin/hf auth login --token ${HF_TOKEN}'

      - name: Run stage-a tests
        timeout-minutes: 30
        run: |
          docker exec ci_sglang_xpu bash -c "source /opt/venv/bin/activate && cd /sglang-checkout/test && python3 run_suite.py --hw xpu --suite stage-a-test-1-gpu-xpu"

      - name: Cleanup container
        if: always()
        run: |
          # pip install ran as root inside the container against the
          # bind-mounted workspace, so build artifacts are root-owned on
          # the host. Chown them back before rm to avoid Permission denied.
          docker run --rm -v "${{ github.workspace }}:/w" busybox:latest \
            chown -R "$(id -u):$(id -g)" /w || true
          # Wipe everything the run wrote into the workspace so the next
          # job starts from a clean tree.
          rm -rf \
            python/build \
            python/dist \
            python/sglang.egg-info \
            python/sglang/*.egg-info \
            test/result.jsonl \
            test/results \
            test/.pytest_cache \
            .pytest_cache || true
          find . -type d -name "__pycache__" -prune -exec rm -rf {} + || true
          find . -type f -name "*.pyc" -delete || true
          docker rm -f ci_sglang_xpu || true
          if [[ -n "${CI_SGLANG_XPU_IMAGE:-}" ]]; then
            docker rmi -f "${CI_SGLANG_XPU_IMAGE}" || true
          fi

  # ==================== Wait for Stage A ==================== #
  wait-for-stage-a:
    needs: [stage-a-test-1-gpu-xpu]
    runs-on: ubuntu-latest
    steps:
      - run: echo "stage-a passed"

  # ==================== Stage B ==================== #
  stage-b-test-1-gpu-xpu:
    needs: [check-changes, pr-gate, wait-for-stage-a]
    if: needs.check-changes.outputs.main_package == 'true'
    runs-on: intel-bmg
    env:
      DOCKERHUB_INTEL_USERNAME: ${{ secrets.DOCKERHUB_INTEL_USERNAME }}
      DOCKERHUB_INTEL_TOKEN: ${{ secrets.DOCKERHUB_INTEL_TOKEN }}
    steps:
      - name: Reset workspace ownership
        run: |
          docker run --rm -v "${{ github.workspace }}:/w" busybox:latest \
            chown -R "$(id -u):$(id -g)" /w || true

      - name: Checkout code
        uses: actions/checkout@v4
        with:
          fetch-depth: 0
          ref: ${{ inputs.ref || github.ref }}

      - name: Start CI container
        run: |
          export HF_TOKEN="$(cat ~/huggingface_token.txt)"
          bash scripts/ci/xpu/xpu_ci_start_container.sh
        env:
          GITHUB_WORKSPACE: ${{ github.workspace }}

      - name: Install Dependency
        timeout-minutes: 60
        run: |
          docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install --upgrade pip
          docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install pytest expecttest ray huggingface_hub tabulate
          docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip uninstall -y flashinfer-python sgl-kernel sglang
          docker exec ci_sglang_xpu cp /sglang-checkout/python/pyproject_xpu.toml /sglang-checkout/python/pyproject.toml
          docker exec -w /sglang-checkout/python ci_sglang_xpu /opt/venv/bin/python3 -m pip install --no-cache-dir . --extra-index-url https://download.pytorch.org/whl/xpu
          docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install --no-cache-dir --no-deps xgrammar==0.1.33
          docker exec ci_sglang_xpu /bin/bash -c '/opt/venv/bin/hf auth login --token ${HF_TOKEN}'

      - name: Run stage-b tests
        timeout-minutes: 60
        run: |
          docker exec ci_sglang_xpu bash -c "source /opt/venv/bin/activate && cd /sglang-checkout/test && python3 run_suite.py --hw xpu --suite stage-b-test-1-gpu-xpu"

      - name: Cleanup container
        if: always()
        run: |
          # pip install ran as root inside the container against the
          # bind-mounted workspace, so build artifacts are root-owned on
          # the host. Chown them back before rm to avoid Permission denied.
          docker run --rm -v "${{ github.workspace }}:/w" busybox:latest \
            chown -R "$(id -u):$(id -g)" /w || true
          # Wipe everything the run wrote into the workspace so the next
          # job starts from a clean tree.
          rm -rf \
            python/build \
            python/dist \
            python/sglang.egg-info \
            python/sglang/*.egg-info \
            test/result.jsonl \
            test/results \
            test/.pytest_cache \
            .pytest_cache || true
          find . -type d -name "__pycache__" -prune -exec rm -rf {} + || true
          find . -type f -name "*.pyc" -delete || true
          docker rm -f ci_sglang_xpu || true
          if [[ -n "${CI_SGLANG_XPU_IMAGE:-}" ]]; then
            docker rmi -f "${CI_SGLANG_XPU_IMAGE}" || true
          fi

  finish:
    if: always()
    needs: [stage-a-test-1-gpu-xpu, stage-b-test-1-gpu-xpu, pr-gate]
    runs-on: ubuntu-latest
    steps:
      - name: Check job status
        run: |
          stage_a="${{ needs.stage-a-test-1-gpu-xpu.result }}"
          stage_b="${{ needs.stage-b-test-1-gpu-xpu.result }}"
          if [ "$stage_a" != "success" ] && [ "$stage_a" != "skipped" ]; then
            echo "stage-a failed with result: $stage_a"
            exit 1
          fi
          if [ "$stage_b" != "success" ] && [ "$stage_b" != "skipped" ]; then
            echo "stage-b failed with result: $stage_b"
            exit 1
          fi
          echo "All jobs completed successfully"
          exit 0