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

View File

@@ -1610,55 +1610,57 @@ jobs:
with:
artifact-suffix: ${{ matrix.part }}
stage-c-test-4-gpu-gb200:
needs: [check-changes, call-gate, wait-for-stage-b, sgl-kernel-build-wheels-arm]
if: |
always() &&
(
(inputs.target_stage == 'stage-c-test-4-gpu-gb200') ||
(
!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:
RUNNER_LABELS: 4-gpu-gb200
strategy:
fail-fast: false
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Download artifacts
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9-aarch64
- name: Install dependencies
timeout-minutes: 20
run: |
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/cuda/ci_install_deepep.sh
- name: Run test
timeout-minutes: 45
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
python3 run_suite.py --hw cuda --suite stage-c-test-4-gpu-gb200 --timeout-per-file 3600 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
# NOTE: GB200 stage temporarily disabled — no company-owned GB200 runner available yet.
# Re-enable when a 4-gpu-gb200 runner is provisioned.
# stage-c-test-4-gpu-gb200:
# needs: [check-changes, call-gate, wait-for-stage-b, sgl-kernel-build-wheels-arm]
# if: |
# always() &&
# (
# (inputs.target_stage == 'stage-c-test-4-gpu-gb200') ||
# (
# !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:
# RUNNER_LABELS: 4-gpu-gb200
# strategy:
# fail-fast: false
# steps:
# - name: Checkout code
# uses: actions/checkout@v4
# with:
# ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
#
# - name: Download artifacts
# if: needs.check-changes.outputs.sgl_kernel == 'true'
# uses: actions/download-artifact@v4
# with:
# path: sgl-kernel/dist/
# merge-multiple: true
# pattern: wheel-python3.10-cuda12.9-aarch64
#
# - name: Install dependencies
# timeout-minutes: 20
# run: |
# CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/cuda/ci_install_deepep.sh
#
# - name: Run test
# timeout-minutes: 45
# 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
# python3 run_suite.py --hw cuda --suite stage-c-test-4-gpu-gb200 --timeout-per-file 3600 $CONTINUE_ON_ERROR_FLAG
#
# - uses: ./.github/actions/upload-cuda-coredumps
# if: always()
pr-test-finish:
needs:
@@ -1692,7 +1694,7 @@ jobs:
stage-c-test-deepep-4-gpu,
stage-c-test-deepep-8-gpu-h200,
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()
runs-on: ubuntu-latest