chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[CI] Revive 8-GPU trace upload in nightly test workflow (#18820)

Browse Source 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Kangyan-Zhou
2026-02-14 08:37:08 +08:00
committed by GitHub
parent 1be41e9036
commit eccf875d49
2 changed files with 70 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
.github/workflows/nightly-test-nvidia.yml vendored
View File

@@ -120,6 +120,25 @@ jobs:
cd test
python3 run_suite.py --hw cuda --suite nightly-8-gpu-common --nightly --timeout-per-file=18000 --continue-on-error --auto-partition-id=${{ matrix.partition }} --auto-partition-size=4
- name: Publish traces to storage repo
if: always()
continue-on-error: true
env:
GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
GITHUB_RUN_ID: ${{ github.run_id }}
GITHUB_RUN_NUMBER: ${{ github.run_number }}
run: |
TRACE_ARGS=""
for dir in test/performance_profiles_*/; do
[ -d "$dir" ] && TRACE_ARGS="$TRACE_ARGS --traces-dir $dir"
done
if [ -n "$TRACE_ARGS" ]; then
python3 scripts/ci/utils/publish_traces.py $TRACE_ARGS
find test/performance_profiles_*/ -name '*.json.gz' -delete
else
echo "No trace directories found, skipping publish"
fi
- name: Run test
timeout-minutes: 30
env:
@@ -201,6 +220,25 @@ jobs:
cd test
IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite nightly-8-gpu-common --nightly --timeout-per-file=12000 --continue-on-error --auto-partition-id=${{ matrix.partition }} --auto-partition-size=4
- name: Publish traces to storage repo
if: always()
continue-on-error: true
env:
GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
GITHUB_RUN_ID: ${{ github.run_id }}
GITHUB_RUN_NUMBER: ${{ github.run_number }}
run: |
TRACE_ARGS=""
for dir in test/performance_profiles_*/; do
[ -d "$dir" ] && TRACE_ARGS="$TRACE_ARGS --traces-dir $dir"
done
if [ -n "$TRACE_ARGS" ]; then
python3 scripts/ci/utils/publish_traces.py $TRACE_ARGS
find test/performance_profiles_*/ -name '*.json.gz' -delete
else
echo "No trace directories found, skipping publish"
fi
- name: Collect performance metrics
if: always()
run: |