ci: temporarily disable GB200 test stage (#19289)

This commit is contained in:
Alison Shao
2026-02-24 19:04:23 -08:00
committed by GitHub
parent 0fac2796b6
commit f862214c67
+52 -50
View File
@@ -1610,55 +1610,57 @@ jobs:
with: with:
artifact-suffix: ${{ matrix.part }} artifact-suffix: ${{ matrix.part }}
stage-c-test-4-gpu-gb200: # NOTE: GB200 stage temporarily disabled — no company-owned GB200 runner available yet.
needs: [check-changes, call-gate, wait-for-stage-b, sgl-kernel-build-wheels-arm] # Re-enable when a 4-gpu-gb200 runner is provisioned.
if: | # stage-c-test-4-gpu-gb200:
always() && # needs: [check-changes, call-gate, wait-for-stage-b, sgl-kernel-build-wheels-arm]
( # if: |
(inputs.target_stage == 'stage-c-test-4-gpu-gb200') || # always() &&
( # (
!inputs.target_stage && # (inputs.target_stage == 'stage-c-test-4-gpu-gb200') ||
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) && # (
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true')) # !inputs.target_stage &&
) # ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
) # ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 4-gpu-gb200 # )
timeout-minutes: 240 # )
env: # runs-on: 4-gpu-gb200
RUNNER_LABELS: 4-gpu-gb200 # timeout-minutes: 240
strategy: # env:
fail-fast: false # RUNNER_LABELS: 4-gpu-gb200
steps: # strategy:
- name: Checkout code # fail-fast: false
uses: actions/checkout@v4 # steps:
with: # - name: Checkout code
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }} # uses: actions/checkout@v4
# with:
- name: Download artifacts # ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
if: needs.check-changes.outputs.sgl_kernel == 'true' #
uses: actions/download-artifact@v4 # - name: Download artifacts
with: # if: needs.check-changes.outputs.sgl_kernel == 'true'
path: sgl-kernel/dist/ # uses: actions/download-artifact@v4
merge-multiple: true # with:
pattern: wheel-python3.10-cuda12.9-aarch64 # path: sgl-kernel/dist/
# merge-multiple: true
- name: Install dependencies # pattern: wheel-python3.10-cuda12.9-aarch64
timeout-minutes: 20 #
run: | # - name: Install dependencies
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/cuda/ci_install_deepep.sh # timeout-minutes: 20
# run: |
- name: Run test # CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/cuda/ci_install_deepep.sh
timeout-minutes: 45 #
run: | # - name: Run test
cd test # timeout-minutes: 45
CONTINUE_ON_ERROR_FLAG="" # run: |
if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then # cd test
CONTINUE_ON_ERROR_FLAG="--continue-on-error" # CONTINUE_ON_ERROR_FLAG=""
fi # if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
python3 run_suite.py --hw cuda --suite stage-c-test-4-gpu-gb200 --timeout-per-file 3600 $CONTINUE_ON_ERROR_FLAG # CONTINUE_ON_ERROR_FLAG="--continue-on-error"
# fi
- uses: ./.github/actions/upload-cuda-coredumps # python3 run_suite.py --hw cuda --suite stage-c-test-4-gpu-gb200 --timeout-per-file 3600 $CONTINUE_ON_ERROR_FLAG
if: always() #
# - uses: ./.github/actions/upload-cuda-coredumps
# if: always()
pr-test-finish: pr-test-finish:
needs: needs:
@@ -1692,7 +1694,7 @@ jobs:
stage-c-test-deepep-4-gpu, stage-c-test-deepep-4-gpu,
stage-c-test-deepep-8-gpu-h200, stage-c-test-deepep-8-gpu-h200,
stage-c-test-4-gpu-b200, stage-c-test-4-gpu-b200,
stage-c-test-4-gpu-gb200, # stage-c-test-4-gpu-gb200, # Temporarily disabled — no GB200 runner
] ]
if: always() if: always()
runs-on: ubuntu-latest runs-on: ubuntu-latest