chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[CI] Fix max_parallel for scheduled runs (#17046)

Browse Source
This commit is contained in:
Alison Shao
2026-01-13 20:16:32 -08:00
committed by GitHub
parent a5348eac4c
commit 9479eca75d
1 changed files with 55 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

106
.github/workflows/pr-test.yml vendored
View File

@@ -110,12 +110,16 @@ jobs:
- "python/*.toml"
- ".github/workflows/pr-test.yml"
- name: Set max-parallel based on high-priority label
- name: Set max-parallel based on run type
id: set-parallel
run: |
if [[ "${{ github.event_name }}" == "pull_request" && "${{ contains(github.event.pull_request.labels.*.name, 'high priority') }}" == "true" ]]; then
echo "max_parallel=15" >> $GITHUB_OUTPUT
echo "High priority PR detected, setting max_parallel to 15"
# Scheduled runs and high-priority PRs get full parallelism
if [[ "${{ github.event_name }}" == "schedule" ]]; then
echo "max_parallel=14" >> $GITHUB_OUTPUT
echo "Scheduled run detected, setting max_parallel to 14"
elif [[ "${{ github.event_name }}" == "pull_request" && "${{ contains(github.event.pull_request.labels.*.name, 'high priority') }}" == "true" ]]; then
echo "max_parallel=14" >> $GITHUB_OUTPUT
echo "High priority PR detected, setting max_parallel to 14"
else
echo "max_parallel=3" >> $GITHUB_OUTPUT
echo "Using default max_parallel of 3"
@@ -772,6 +776,53 @@ jobs:
fi
python3 run_suite.py --hw cuda --suite stage-b-test-large-2-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 2 $CONTINUE_ON_ERROR_FLAG
stage-b-test-4-gpu-b200:
needs: [check-changes, call-gate, stage-a-test-1, sgl-kernel-build-wheels]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-4-gpu-b200') ||
(
!inputs.target_stage &&
(github.event_name == 'schedule' || (!failure() && !cancelled())) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
runs-on: ${{ needs.check-changes.outputs.b200_runner }}
env:
RUNNER_LABELS: ${{ needs.check-changes.outputs.b200_runner }}
strategy:
fail-fast: false
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Download artifacts
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v6
with:
path: sgl-kernel/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
- name: Install dependencies
timeout-minutes: 10
run: |
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
cd test
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite stage-b-test-4-gpu-b200 $CONTINUE_ON_ERROR_FLAG
stage-c-test-large-4-gpu:
needs: [check-changes, call-gate, stage-b-test-small-1-gpu, stage-b-test-large-1-gpu, stage-b-test-large-2-gpu, sgl-kernel-build-wheels]
if: |
@@ -1002,53 +1053,6 @@ jobs:
fi
python3 run_suite.py --suite quantization_test $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
stage-b-test-4-gpu-b200:
needs: [check-changes, call-gate, stage-a-test-1, sgl-kernel-build-wheels]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-4-gpu-b200') ||
(
!inputs.target_stage &&
(github.event_name == 'schedule' || (!failure() && !cancelled())) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
runs-on: ${{ needs.check-changes.outputs.b200_runner }}
env:
RUNNER_LABELS: ${{ needs.check-changes.outputs.b200_runner }}
strategy:
fail-fast: false
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Download artifacts
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v6
with:
path: sgl-kernel/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
- name: Install dependencies
timeout-minutes: 10
run: |
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
cd test
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
fi
IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite stage-b-test-4-gpu-b200 $CONTINUE_ON_ERROR_FLAG
unit-test-backend-4-gpu:
needs: [check-changes, call-gate, stage-b-test-small-1-gpu, stage-b-test-large-1-gpu, stage-b-test-large-2-gpu, stage-b-test-4-gpu-b200]
if: |