sglang/.github/workflows/pr-test-extra.yml

name: PR Test Extra
# Label-gated CI for nightly-class tests opted into a per-PR run.
#
# Adds runtime to a PR only when the author asks for it: pull_request
# events bail unless the PR carries the `run-ci-extra` label. The same job
# graph runs unconditionally on workflow_dispatch / workflow_call so it
# can be triggered manually or chained from another workflow.
#
# Stages: extra-a (1-/2-gpu) and extra-b (4-/8-gpu) caller stubs reuse
# `_pr-test-stage.yml` and `_pr-test-check-changes.yml` from pr-test.yml.

run-name: ${{ inputs.target_stage && (inputs.pr_head_sha && format('[{0}] {1}', inputs.target_stage, inputs.pr_head_sha) || format('[{0}]', inputs.target_stage)) || '' }}

on:
  pull_request:
    branches: [main]
  workflow_dispatch:
    inputs:
      target_stage:
        description: "Specific stage to run (optional, for quick testing)"
        required: false
        type: string
        default: ""
      force_continue_on_error:
        description: "Force continue-on-error (test scheduled CI behavior)"
        required: false
        type: boolean
        default: false
      pr_head_sha:
        description: "PR head SHA to checkout (for /rerun-stage on fork PRs)"
        required: false
        type: string
        default: ""
      include_wheel_build:
        description: "When set with target_stage, also run sgl-kernel-build-wheels so the target stage uses the freshly-built kernel (for /rerun-stage on PRs that modify sgl-kernel/)"
        required: false
        type: boolean
        default: false
      test_parallel_dispatch:
        description: "Test parallel dispatch behavior (simulates scheduled run)"
        required: false
        type: boolean
        default: false
  workflow_call:
    inputs:
      git_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
      skip_stage_health_check:
        description: "Skip stage health check fast-fail (e.g. for release branch cuts)"
        required: false
        type: boolean
        default: false

concurrency:
  group: pr-test-extra-${{ github.event_name }}-${{ github.head_ref || github.ref_name || 'default' }}-${{ inputs.pr_head_sha || 'current' }}-${{ inputs.target_stage || inputs.git_ref || 'all' }}
  cancel-in-progress: ${{ github.event_name != 'workflow_call' }}

env:
  SGLANG_IS_IN_CI: true
  SGLANG_CUDA_COREDUMP: "1"
  SGLANG_JIT_DEEPGEMM_FAST_WARMUP: true
  SKIP_STAGE_HEALTH_CHECK: ${{ (inputs.skip_stage_health_check == true || inputs.run_all_tests == true) && 'true' || 'false' }}
  FORCE_REBUILD_DEEPEP: '1'
  PR_TEST_BYPASS_MAINTENANCE_ON_MAIN: ${{ github.ref == 'refs/heads/main' && 'true' || 'false' }}
  USE_VENV: false

permissions:
  actions: write
  contents: read
  issues: read
  pull-requests: read

jobs:
  # =============================================== check changes ====================================================
  # Label gate: pull_request events only proceed when the PR carries BOTH
  # `run-ci` and `run-ci-extra` labels — `run-ci` is the basic-CI prerequisite
  # (matching pr-test.yml's pr-gate `require-run-ci`) and `run-ci-extra` is the
  # explicit opt-in to this workflow. Other event types
  # (workflow_dispatch / workflow_call) always run. When this job is
  # skipped by the gate, every downstream caller stub naturally skips
  # because its needs do not resolve.
  check-changes:
    if: |
      github.event_name != 'pull_request' ||
      (
        contains(github.event.pull_request.labels.*.name, 'run-ci') &&
        contains(github.event.pull_request.labels.*.name, 'run-ci-extra')
      )
    uses: ./.github/workflows/_pr-test-check-changes.yml
    with:
      pr_head_sha: ${{ inputs.pr_head_sha || '' }}
      git_ref: ${{ inputs.git_ref || '' }}
      target_stage: ${{ inputs.target_stage || '' }}
      include_wheel_build: ${{ inputs.include_wheel_build == true }}
      run_all_tests: ${{ inputs.run_all_tests == true }}
      force_continue_on_error: ${{ inputs.force_continue_on_error == true }}
      pr_test_yml: '.github/workflows/pr-test-extra.yml'
    secrets: inherit

  # always(): on a PR without `run-ci-extra` the rest of this workflow's graph
  # is skipped, but we still want the awareness block updated so the author
  # sees this run was a no-op.
  call-pr-awareness:
    needs: check-changes
    if: always() && github.event_name == 'pull_request'
    permissions:
      pull-requests: write
    uses: ./.github/workflows/_pr-awareness-comment.yml
    with:
      workflow_kind: pr-test-extra
    secrets: inherit

  # =============================================== sgl-kernel ====================================================
  sgl-kernel-build-wheels:
    needs: check-changes
    if: |
      always() &&
      needs.check-changes.result == 'success' &&
      needs.check-changes.outputs.sgl_kernel == 'true' &&
      (!inputs.target_stage || inputs.include_wheel_build)
    uses: ./.github/workflows/_pr-test-sgl-kernel-build.yml
    with:
      runs_on: x64-kernel-build-node
      job_display_name: Build Wheel
      pr_head_sha: ${{ inputs.pr_head_sha || '' }}
      git_ref: ${{ inputs.git_ref || '' }}
      skip_stage_health_check: ${{ inputs.skip_stage_health_check == true }}
    secrets: inherit

  # =============================================== extra-a (1-/2-gpu) ===============================================
  extra-a-test-1-gpu-small:
    needs: [check-changes, sgl-kernel-build-wheels]
    if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' }}
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: extra-a-test-1-gpu-small
      runner_config: 1-gpu-small
      runs_on: 1-gpu-5090
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '60'
    secrets: inherit

  extra-a-test-1-gpu-large:
    needs: [check-changes, sgl-kernel-build-wheels]
    if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' }}
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: extra-a-test-1-gpu-large
      runner_config: 1-gpu-large
      runs_on: 1-gpu-h100
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '60'
      timeout_per_file: '1800'
    secrets: inherit

  extra-a-test-2-gpu-large:
    needs: [check-changes, sgl-kernel-build-wheels]
    if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' }}
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: extra-a-test-2-gpu-large
      runner_config: 2-gpu-large
      runs_on: 2-gpu-h100
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '60'
    secrets: inherit

  # =============================================== extra-b (4-/8-gpu) ===============================================
  extra-b-test-4-gpu-h100:
    needs: [check-changes, sgl-kernel-build-wheels]
    if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' }}
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: extra-b-test-4-gpu-h100
      runner_config: 4-gpu-h100
      runs_on: 4-gpu-h100
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '60'
    secrets: inherit

  extra-b-test-4-gpu-b200:
    needs: [check-changes, sgl-kernel-build-wheels]
    if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' }}
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: extra-b-test-4-gpu-b200
      runner_config: 4-gpu-b200
      runs_on: ${{ needs.check-changes.outputs.b200_runner }}
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '60'
      timeout_per_file: '1800'
    secrets: inherit

  extra-b-test-8-gpu-h200:
    needs: [check-changes, sgl-kernel-build-wheels]
    if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' }}
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: extra-b-test-8-gpu-h200
      runner_config: 8-gpu-h200
      runs_on: 8-gpu-h200
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '60'
    secrets: inherit

  extra-b-test-deepep-8-gpu-h200:
    needs: [check-changes, sgl-kernel-build-wheels]
    if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' }}
    uses: ./.github/workflows/_pr-test-stage.yml
    with:
      self_name: extra-b-test-deepep-8-gpu-h200
      runner_config: deepep-8-gpu-h200
      runs_on: 8-gpu-h200-deepep
      check_changes: ${{ toJson(needs.check-changes.outputs) }}
      caller_inputs: ${{ toJson(inputs) }}
      partitions: ${{ needs.check-changes.outputs.partitions }}
      run_timeout_minutes: '60'
    secrets: inherit