sglang/.github/workflows/pr-test-jit-kernel.yml

name: PR Test - JIT Kernel

on:
  workflow_call:
    inputs:
      jit_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: ''
      target_stage:
        required: false
        type: string
        default: ''
      test_parallel_dispatch:
        required: false
        type: string
        default: 'false'
      skip_stage_health_check:
        required: false
        type: boolean
        default: false

# Workflow-level env is NOT inherited from the caller in reusable workflows (verified by CI test).
# The github context (including github.event_name) IS inherited from the caller.
env:
  SGLANG_IS_IN_CI: true
  SGLANG_CUDA_COREDUMP: "1"
  SGLANG_JIT_DEEPGEMM_FAST_WARMUP: true
  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:
  jit-kernel-unit-test:
    if: |
      github.event_name != 'schedule' &&
      inputs.test_parallel_dispatch != 'true' &&
      !inputs.target_stage
    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: Install dependencies
        timeout-minutes: 20
        run: |
          bash scripts/ci/cuda/ci_install_dependency.sh diffusion

      - name: Run test
        timeout-minutes: 30
        run: |
          cd test/
          python3 run_suite.py --hw cuda --suite stage-b-kernel-unit-1-gpu-large

  jit-kernel-multigpu-unit-test:
    if: |
      github.event_name != 'schedule' &&
      inputs.test_parallel_dispatch != 'true' &&
      !inputs.target_stage
    runs-on: 8-gpu-h200
    timeout-minutes: 240
    steps:
      - uses: actions/checkout@v4
        with:
          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}

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

      - name: Install dependencies
        timeout-minutes: 20
        run: |
          bash scripts/ci/cuda/ci_install_dependency.sh diffusion

      - name: Run multi-GPU test
        timeout-minutes: 45
        run: |
          cd test/
          python3 run_suite.py --hw cuda --suite stage-b-kernel-unit-8-gpu-h200

  jit-kernel-benchmark-test:
    if: |
      github.event_name != 'schedule' &&
      inputs.test_parallel_dispatch != 'true' &&
      !inputs.target_stage
    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: Install dependencies
        timeout-minutes: 20
        run: |
          bash scripts/ci/cuda/ci_install_dependency.sh diffusion

      - name: Run benchmark tests
        timeout-minutes: 45
        run: |
          cd test/
          python3 run_suite.py --hw cuda --suite stage-b-kernel-benchmark-1-gpu-large

  jit-kernel-b200-test:
    if: |
      github.event_name != 'schedule' &&
      inputs.test_parallel_dispatch != 'true' &&
      !inputs.target_stage
    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: Install dependencies
        timeout-minutes: 20
        run: |
          bash scripts/ci/cuda/ci_install_dependency.sh diffusion

      - name: Run B200 diffusion test
        timeout-minutes: 30
        run: |
          cd test/
          python3 run_suite.py --hw cuda --suite stage-b-kernel-unit-1-gpu-b200