Skip to content

[CI] Temp disable gb200 test #14865

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Fridge003 merged 1 commit into from
Dec 11, 2025
Merged

[CI] Temp disable gb200 test #14865

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
73 changes: 37 additions & 36 deletions .github/workflows/pr-test.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1216,44 +1216,45 @@ jobs:
cd test/srt
python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 1800

unit-test-backend-4-gpu-gb200:
needs: [check-changes, call-gate, unit-test-backend-2-gpu, 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
env:
RUNNER_LABELS: 4-gpu-gb200
strategy:
fail-fast: false
steps:
- name: Checkout code
uses: actions/checkout@v4
# TODO: Add gb200 tests back after the ci runner is fixed
# unit-test-backend-4-gpu-gb200:
# needs: [check-changes, call-gate, unit-test-backend-2-gpu, 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
# env:
# RUNNER_LABELS: 4-gpu-gb200
# strategy:
# fail-fast: false
# steps:
# - name: Checkout code
# uses: actions/checkout@v4

- 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: 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
run: |
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/ci_install_deepep.sh
# - name: Install dependencies
# run: |
# CUSTOM_BUILD_SGL_KERNEL=${{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
python3 run_suite.py --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600
# - name: Run test
# timeout-minutes: 45
# run: |
# cd test/srt
# python3 run_suite.py --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600

pr-test-finish:
needs:
Expand Down Expand Up @@ -1287,7 +1288,7 @@ jobs:
unit-test-deepep-4-gpu,
unit-test-deepep-8-gpu,
unit-test-backend-4-gpu-b200,
unit-test-backend-4-gpu-gb200,
# unit-test-backend-4-gpu-gb200,
# unit-test-backend-8-gpu-b200, # Moved to nightly - large models only
]
if: always()
Expand Down
Loading