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

Disable unit-test-backend-4-gpu-gb200 job (#17367)

Browse Source
This commit is contained in:
Alison Shao
2026-01-19 14:35:58 -08:00
committed by GitHub
parent 91d8c52d6d
commit 057b07fc50
1 changed files with 52 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test.yml
+52 -51
View File
@@ -1541,56 +1541,57 @@ jobs:
fi fi
IS_BLACKWELL=1 python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 1800 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG IS_BLACKWELL=1 python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 1800 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
unit-test-backend-4-gpu-gb200: # Disabled: GB200 runner needs repair
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, sgl-kernel-build-wheels-arm] # unit-test-backend-4-gpu-gb200:
if: | # 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, sgl-kernel-build-wheels-arm]
always() && # if: |
( # always() &&
(inputs.target_stage == 'unit-test-backend-4-gpu-gb200') || # (
( # (inputs.target_stage == 'unit-test-backend-4-gpu-gb200') ||
!inputs.target_stage && # (
(github.event_name == 'schedule' || (!failure() && !cancelled())) && # !inputs.target_stage &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) # (github.event_name == 'schedule' || (!failure() && !cancelled())) &&
) # ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
) # )
runs-on: 4-gpu-gb200 # )
timeout-minutes: 60 # runs-on: 4-gpu-gb200
env: # timeout-minutes: 60
RUNNER_LABELS: 4-gpu-gb200 # env:
strategy: # RUNNER_LABELS: 4-gpu-gb200
fail-fast: false # strategy:
steps: # fail-fast: false
- name: Checkout code # steps:
uses: actions/checkout@v4 # - name: Checkout code
with: # uses: actions/checkout@v4
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }} # with:
# ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Download artifacts #
if: needs.check-changes.outputs.sgl_kernel == 'true' # - name: Download artifacts
uses: actions/download-artifact@v4 # if: needs.check-changes.outputs.sgl_kernel == 'true'
with: # uses: actions/download-artifact@v4
path: sgl-kernel/dist/ # with:
merge-multiple: true # path: sgl-kernel/dist/
pattern: wheel-python3.10-cuda12.9-aarch64 # merge-multiple: true
# pattern: wheel-python3.10-cuda12.9-aarch64
- name: Install dependencies #
timeout-minutes: 10 # - name: Install dependencies
run: | # timeout-minutes: 10
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/ci_install_deepep.sh # run: |
# CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/ci_install_deepep.sh
- name: Run test #
timeout-minutes: 45 # - name: Run test
run: | # timeout-minutes: 45
cd test/srt # run: |
RETRY_FLAG="" # cd test/srt
if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then # RETRY_FLAG=""
RETRY_FLAG="--enable-retry" # if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
fi # RETRY_FLAG="--enable-retry"
CONTINUE_ON_ERROR_FLAG="" # fi
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then # CONTINUE_ON_ERROR_FLAG=""
CONTINUE_ON_ERROR_FLAG="--continue-on-error" # if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
fi # CONTINUE_ON_ERROR_FLAG="--continue-on-error"
python3 run_suite.py --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG # fi
# python3 run_suite.py --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
pr-test-finish: pr-test-finish:
needs: needs:
@@ -1627,7 +1628,7 @@ jobs:
unit-test-deepep-4-gpu, unit-test-deepep-4-gpu,
# unit-test-deepep-8-gpu, # Disabled, see #17175 # unit-test-deepep-8-gpu, # Disabled, see #17175
unit-test-backend-4-gpu-b200, unit-test-backend-4-gpu-b200,
unit-test-backend-4-gpu-gb200, # unit-test-backend-4-gpu-gb200, # Disabled: GB200 runner needs repair
] ]
if: always() if: always()
runs-on: ubuntu-latest runs-on: ubuntu-latest