Files
wehub-resource-sync 94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:38:16 +08:00

321 lines
14 KiB
YAML

name: PR Test Extra
# Label-gated extra CI workflow opted into per-PR via labels.
#
# Adds runtime to a PR only when the author asks for it: the PR must carry
# BOTH `run-ci` (basic-CI prerequisite) and `run-ci-extra` (explicit opt-in
# to this workflow). The label check happens at runtime in pr-gate.yml via
# live `gh pr view --json labels`, so reruns after adding the labels via
# slash command pick up the new label set (workflow-level `if` checks would
# read the frozen event payload, which never updates on rerun). 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:
# `labeled` lets the workflow re-fire when `run-ci-extra` (or `run-ci`)
# is added after the latest push — otherwise GHA leaves the stale
# skipped run in place and there's no way to enable extra without
# another push. See check-changes.if below for the matching guard.
types: [opened, synchronize, reopened, labeled]
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
run_all_tests:
description: "Run all tests — bypasses paths-filter (needed when dispatching against long-lived branches whose diff against main can't resolve a merge-base in a shallow clone)"
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 ====================================================
# The actual `run-ci` + `run-ci-extra` label gate now lives in the
# `call-gate` job below, which calls pr-gate.yml. pr-gate.yml live-fetches
# the PR's current labels at runtime, so a rerun (e.g. via
# /tag-and-rerun-ci extra, which adds labels via GITHUB_TOKEN — these
# don't cascade-trigger labeled events) picks up the new label set and
# passes. The previous workflow-level `if` checked the frozen event
# payload, which never updates on rerun and made the slash-add-label flow
# impossible to recover.
#
# We only keep one filter here: for `labeled` events, only proceed if the
# just-added label is one of the gating labels. This prevents every
# unrelated label addition from dispatching a full CI run.
check-changes:
if: |
github.event_name != 'pull_request' ||
github.event.action != 'labeled' ||
github.event.label.name == 'run-ci' ||
github.event.label.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
# =============================================== PR Gate ====================================================
# Runtime live-fetch gate. Mirrors pr-test.yml's call-gate, but additionally
# requires `run-ci-extra`. Failure here cascades down to every test job
# via `needs`, so the workflow ends with one red gate job (~30s) plus a
# row of skipped test jobs instead of consuming a runner.
call-gate:
needs: check-changes
if: github.event_name != 'schedule' && needs.check-changes.result == 'success'
uses: ./.github/workflows/pr-gate.yml
with:
require-run-ci: true
require-run-ci-extra: true
secrets: inherit
# =============================================== sgl-kernel ====================================================
sgl-kernel-build-wheels:
needs: [check-changes, call-gate]
if: |
needs.check-changes.result == 'success' &&
(needs.call-gate.result == 'success' || needs.call-gate.result == 'skipped') &&
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, call-gate, sgl-kernel-build-wheels]
if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' && (needs.call-gate.result == 'success' || needs.call-gate.result == 'skipped') }}
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, call-gate, sgl-kernel-build-wheels]
if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' && (needs.call-gate.result == 'success' || needs.call-gate.result == 'skipped') }}
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, call-gate, sgl-kernel-build-wheels]
if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' && (needs.call-gate.result == 'success' || needs.call-gate.result == 'skipped') }}
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, call-gate, sgl-kernel-build-wheels]
if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' && (needs.call-gate.result == 'success' || needs.call-gate.result == 'skipped') }}
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, call-gate, sgl-kernel-build-wheels]
if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' && (needs.call-gate.result == 'success' || needs.call-gate.result == 'skipped') }}
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, call-gate, sgl-kernel-build-wheels]
if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' && (needs.call-gate.result == 'success' || needs.call-gate.result == 'skipped') }}
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-4-gpu-h100:
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' && (needs.call-gate.result == 'success' || needs.call-gate.result == 'skipped') }}
uses: ./.github/workflows/_pr-test-stage.yml
with:
self_name: extra-b-test-deepep-4-gpu-h100
runner_config: deepep-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-deepep-4-gpu-b200:
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' && (needs.call-gate.result == 'success' || needs.call-gate.result == 'skipped') }}
uses: ./.github/workflows/_pr-test-stage.yml
with:
self_name: extra-b-test-deepep-4-gpu-b200
runner_config: deepep-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-deepep-8-gpu-h200:
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
if: ${{ !failure() && !cancelled() && needs.check-changes.result == 'success' && (needs.call-gate.result == 'success' || needs.call-gate.result == 'skipped') }}
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: ${{ needs.check-changes.outputs.partitions }}
run_timeout_minutes: '60'
secrets: inherit
# =============================================== aggregator ====================================================
# Mirrors pr-test.yml's `pr-test-finish` so notify-pr-states below only
# depends on one job rather than re-listing every stage. Fails if any
# dependent failed/cancelled.
pr-test-extra-finish:
needs:
[
check-changes,
call-gate,
sgl-kernel-build-wheels,
extra-a-test-1-gpu-small,
extra-a-test-1-gpu-large,
extra-a-test-2-gpu-large,
extra-b-test-4-gpu-h100,
extra-b-test-4-gpu-b200,
extra-b-test-8-gpu-h200,
extra-b-test-deepep-4-gpu-h100,
extra-b-test-deepep-4-gpu-b200,
extra-b-test-deepep-8-gpu-h200,
]
if: always()
runs-on: ubuntu-latest
steps:
- name: Check all dependent job statuses
run: |
json_needs='${{ toJson(needs) }}'
job_names=$(echo "$json_needs" | jq -r 'keys_unsorted[]')
for job in $job_names; do
result=$(echo "$json_needs" | jq -r --arg j "$job" '.[$j].result')
echo "$job: $result"
if [[ "$result" == "failure" || "$result" == "cancelled" ]]; then
echo "The above jobs failed."
exit 1
fi
done
echo "All jobs completed successfully"
exit 0
# =============================================== notify pr-states ====================================================
# Dispatches pr-states.yml after every attempt (initial + every rerun).
# workflow_run.completed only fires on the initial completion (one
# workflow_run record across attempts), so we explicitly dispatch —
# workflow_dispatch is the only event GITHUB_TOKEN can cascade-create.
#
# Fork PRs are excluded: their pull_request GITHUB_TOKEN is forced
# read-only regardless of declared `actions: write`, so dispatch 403s.
# Fork PRs get pr-states updates via the workflow_run subscription
# there (initial completion) and pull_request_target (push / label).
notify-pr-states:
needs: [pr-test-extra-finish]
if: |
always() &&
github.event_name == 'pull_request' &&
github.event.pull_request.head.repo.full_name == github.repository
runs-on: ubuntu-latest
steps:
- name: Dispatch pr-states refresh
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
PR_NUMBER: ${{ github.event.pull_request.number }}
run: |
gh workflow run pr-states.yml \
--repo ${{ github.repository }} \
--ref main \
-f pr_number="$PR_NUMBER"