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

196 lines
7.7 KiB
YAML

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.
on:
pull_request:
branches: [main]
workflow_dispatch:
inputs:
force_continue_on_error:
description: "Force continue-on-error (test scheduled CI behavior)"
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_pr_test_health_check:
description: "Skip PR test 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.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_PR_TEST_HEALTH_CHECK: ${{ (inputs.skip_pr_test_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:
git_ref: ${{ inputs.git_ref || '' }}
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
# =============================================== sgl-kernel ====================================================
sgl-kernel-build-wheels:
needs: check-changes
if: |
needs.check-changes.result == 'success' &&
needs.check-changes.outputs.sgl_kernel == 'true'
uses: ./.github/workflows/_pr-test-sgl-kernel-build.yml
with:
runs_on: x64-kernel-build-node
job_display_name: Build Wheel
git_ref: ${{ inputs.git_ref || '' }}
skip_pr_test_health_check: ${{ inputs.skip_pr_test_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
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
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
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
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
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
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
check_changes: ${{ toJson(needs.check-changes.outputs) }}
caller_inputs: ${{ toJson(inputs) }}
partitions: ${{ needs.check-changes.outputs.partitions }}
run_timeout_minutes: '60'
secrets: inherit