ci: tag-gated nightly migration — foundation + 40 whole-file moves (#24725)
Co-authored-by: hnyls2002 <lsyincs@gmail.com> Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
This commit is contained in:
Alison Shao
co-authored by
hnyls2002
Liangsheng Yin
hnyls2002
Liangsheng Yin
parent
67096f48bf
commit
ba214ef3d3
@@ -21,6 +21,10 @@ on:
|
||||
force_continue_on_error:
|
||||
type: boolean
|
||||
default: false
|
||||
pr_test_yml:
|
||||
description: 'Workflow YAML whose stage `run_timeout_minutes` drives partition sizing.'
|
||||
type: string
|
||||
default: '.github/workflows/pr-test.yml'
|
||||
outputs:
|
||||
main_package:
|
||||
value: ${{ jobs.run.outputs.main_package }}
|
||||
@@ -274,6 +278,7 @@ jobs:
|
||||
python3 scripts/ci/utils/compute_partitions.py \
|
||||
--full-parallel ${{ steps.parallel-mode.outputs.full }} \
|
||||
--partition-model-file /tmp/partition-model.json \
|
||||
--pr-test-yml ${{ inputs.pr_test_yml }} \
|
||||
>> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Set B200 runner tag
|
||||
|
||||
@@ -0,0 +1,225 @@
|
||||
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 && '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
|
||||
|
||||
# =============================================== 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
|
||||
@@ -518,22 +518,6 @@ jobs:
|
||||
warmup_server_models: 'lmsys/sglang-ci-dsv3-test:4'
|
||||
secrets: inherit
|
||||
|
||||
stage-c-test-deepep-8-gpu-h200:
|
||||
needs: [check-changes, call-gate, wait-for-stage-b, sgl-kernel-build-wheels]
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
uses: ./.github/workflows/_pr-test-stage.yml
|
||||
with:
|
||||
self_name: stage-c-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: '45'
|
||||
warmup_deep_gemm_models: 'deepseek-ai/DeepSeek-V3-0324:8 deepseek-ai/DeepSeek-V3.2:8'
|
||||
warmup_server_models: 'deepseek-ai/DeepSeek-V3-0324:8'
|
||||
secrets: inherit
|
||||
|
||||
stage-c-test-4-gpu-b200:
|
||||
needs: [check-changes, call-gate, wait-for-stage-b, sgl-kernel-build-wheels]
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
@@ -606,7 +590,6 @@ jobs:
|
||||
stage-c-test-8-gpu-h20,
|
||||
stage-c-test-8-gpu-h200,
|
||||
stage-c-test-deepep-4-gpu-h100,
|
||||
stage-c-test-deepep-8-gpu-h200,
|
||||
stage-c-test-4-gpu-b200,
|
||||
stage-c-test-dsv4-4-gpu-b200,
|
||||
stage-c-test-dsv4-8-gpu-h200,
|
||||
|
||||
Reference in New Issue
Block a user