name: PR Test - SGL Kernel

on:
  workflow_call:
    inputs:
      sgl_kernel:
        required: true
        type: string
      b200_runner:
        required: true
        type: string
      pr_head_sha:
        required: false
        type: string
        default: ''
      git_ref:
        required: false
        type: string
        default: ''
      skip_stage_health_check:
        required: false
        type: boolean
        default: false

# Workflow-level env is NOT inherited from the caller in reusable workflows.
# The github context (including github.event_name) IS inherited from the caller.
env:
  SGLANG_IS_IN_CI: true
  SGLANG_CUDA_COREDUMP: "1"
  SGLANG_PR_TEST_BYPASS_MAINTENANCE_ON_MAIN: ${{ github.ref == 'refs/heads/main' && 'true' || 'false' }}
  SKIP_STAGE_HEALTH_CHECK: ${{ inputs.skip_stage_health_check == true && 'true' || 'false' }}

jobs:
  sgl-kernel-unit-test:
    runs-on: 1-gpu-h100
    timeout-minutes: 240
    steps:
      - uses: actions/checkout@v4
        with:
          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}

      - uses: ./.github/actions/check-stage-health

      - uses: ./.github/actions/check-maintenance

      - name: Cleanup
        run: |
          ls -alh sgl-kernel/dist || true
          rm -rf sgl-kernel/dist/* || true

      - name: Download artifacts
        uses: actions/download-artifact@v4
        with:
          path: sgl-kernel/dist/
          merge-multiple: true
          pattern: wheel-python3.10-cuda12.9

      - name: Install dependencies
        timeout-minutes: 20
        run: |
          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion

      - name: Run test
        timeout-minutes: 30
        run: |
          cd sgl-kernel
          pytest tests/

  sgl-kernel-mla-test:
    runs-on: 1-gpu-h100
    timeout-minutes: 240
    steps:
      - uses: actions/checkout@v4
        with:
          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}

      - uses: ./.github/actions/check-stage-health

      - uses: ./.github/actions/check-maintenance

      - name: Cleanup
        run: |
          ls -alh sgl-kernel/dist || true
          rm -rf sgl-kernel/dist/* || true

      - name: Download artifacts
        uses: actions/download-artifact@v4
        with:
          path: sgl-kernel/dist/
          merge-multiple: true
          pattern: wheel-python3.10-cuda12.9

      - name: Install dependencies
        timeout-minutes: 20
        run: |
          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh

      - name: Run test
        timeout-minutes: 30
        run: |
          cd test/registered/mla
          python3 test_mla_deepseek_v3.py

  sgl-kernel-benchmark-test:
    runs-on: 1-gpu-h100
    timeout-minutes: 240
    steps:
      - uses: actions/checkout@v4
        with:
          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}

      - uses: ./.github/actions/check-stage-health

      - uses: ./.github/actions/check-maintenance

      - name: Cleanup
        run: |
          ls -alh sgl-kernel/dist || true
          rm -rf sgl-kernel/dist/* || true

      - name: Download artifacts
        uses: actions/download-artifact@v4
        with:
          path: sgl-kernel/dist/
          merge-multiple: true
          pattern: wheel-python3.10-cuda12.9

      - name: Install dependencies
        timeout-minutes: 20
        run: |
          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh

      - name: Run benchmark tests
        timeout-minutes: 45
        run: |
          cd sgl-kernel/benchmark
          echo "Running sgl-kernel benchmark tests in CI mode..."

          echo "CI environment variable: $CI"
          echo "GITHUB_ACTIONS environment variable: $GITHUB_ACTIONS"

          for bench_file in bench_*.py; do
            echo "Testing $bench_file..."
            timeout 60 python3 "$bench_file" || echo "Warning: $bench_file timed out or failed, continuing..."
            echo "Completed $bench_file"
            echo "---"
          done

          echo "All benchmark tests completed!"

  sgl-kernel-b200-test:
    runs-on: ${{ inputs.b200_runner }}
    timeout-minutes: 240
    steps:
      - uses: actions/checkout@v4
        with:
          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}

      - uses: ./.github/actions/check-stage-health

      - uses: ./.github/actions/check-maintenance

      - name: Cleanup
        run: |
          ls -alh sgl-kernel/dist || true
          rm -rf sgl-kernel/dist/* || true

      - name: Download artifacts
        uses: actions/download-artifact@v4
        with:
          path: sgl-kernel/dist/
          merge-multiple: true
          pattern: wheel-python3.10-cuda12.9

      - name: Install dependencies
        timeout-minutes: 20
        run: |
          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion

      - name: Run sgl-kernel unit tests on B200
        timeout-minutes: 30
        run: |
          cd sgl-kernel
          pytest tests/

  # Adding a single CUDA13 smoke test to verify that the kernel builds and runs
  # TODO: Add back this test when it can pass on CI
  # cuda13-kernel-smoke-test:
  #   if: inputs.sgl_kernel == 'true'
  #   runs-on: x64-cu13-kernel-tests
  #   steps:
  #     - uses: actions/checkout@v4

  #     - name: Cleanup
  #       run: |
  #         ls -alh sgl-kernel/dist || true
  #         rm -rf sgl-kernel/dist/* || true

  #     - name: Download CUDA 13.0 artifacts
  #       uses: actions/download-artifact@v4
  #       with:
  #         path: sgl-kernel/dist/
  #         merge-multiple: true
  #         pattern: wheel-python3.10-cuda13.0

  #     - name: Install dependencies
  #       run: |
  #         CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh

  #     - name: Run kernel unit tests
  #       timeout-minutes: 30
  #       run: |
  #         cd sgl-kernel
  #         pytest tests/