chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 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

103
.github/workflows/pr-test.yml vendored
View File

@@ -1541,56 +1541,57 @@ jobs:
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
unit-test-backend-4-gpu-gb200:
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]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-backend-4-gpu-gb200') ||
(
!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: 4-gpu-gb200
timeout-minutes: 60
env:
RUNNER_LABELS: 4-gpu-gb200
strategy:
fail-fast: false
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Download artifacts
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9-aarch64
- name: Install dependencies
timeout-minutes: 10
run: |
CUSTOM_BUILD_SGL_KERNEL=${{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
run: |
cd test/srt
RETRY_FLAG=""
if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
RETRY_FLAG="--enable-retry"
fi
CONTINUE_ON_ERROR_FLAG=""
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
CONTINUE_ON_ERROR_FLAG="--continue-on-error"
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
# Disabled: GB200 runner needs repair
# unit-test-backend-4-gpu-gb200:
# 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]
# if: |
# always() &&
# (
# (inputs.target_stage == 'unit-test-backend-4-gpu-gb200') ||
# (
# !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: 4-gpu-gb200
# timeout-minutes: 60
# env:
# RUNNER_LABELS: 4-gpu-gb200
# strategy:
# fail-fast: false
# steps:
# - name: Checkout code
# uses: actions/checkout@v4
# with:
# ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
#
# - name: Download artifacts
# if: needs.check-changes.outputs.sgl_kernel == 'true'
# uses: actions/download-artifact@v4
# with:
# path: sgl-kernel/dist/
# merge-multiple: true
# pattern: wheel-python3.10-cuda12.9-aarch64
#
# - name: Install dependencies
# timeout-minutes: 10
# run: |
# CUSTOM_BUILD_SGL_KERNEL=${{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
# run: |
# cd test/srt
# RETRY_FLAG=""
# if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
# RETRY_FLAG="--enable-retry"
# fi
# CONTINUE_ON_ERROR_FLAG=""
# if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
# CONTINUE_ON_ERROR_FLAG="--continue-on-error"
# 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:
needs:
@@ -1627,7 +1628,7 @@ jobs:
unit-test-deepep-4-gpu,
# unit-test-deepep-8-gpu, # Disabled, see #17175
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()
runs-on: ubuntu-latest