[NVIDIA] Add CI workloads for GB200 (#12242)

This commit is contained in:
Kaixi Hou
2025-10-30 14:32:03 -07:00
committed by GitHub
parent 7d121448b2
commit c0d02cf4d1
5 changed files with 73 additions and 5 deletions

View File

@@ -784,6 +784,35 @@ jobs:
cd test/srt
python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600
unit-test-backend-4-gpu-gb200:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels]
if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 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
- name: Install dependencies
run: |
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.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
pr-test-finish:
needs:
[
@@ -808,6 +837,7 @@ jobs:
unit-test-deepep-4-gpu,
unit-test-deepep-8-gpu,
unit-test-backend-4-gpu-b200,
unit-test-backend-4-gpu-gb200,
]
if: always()
runs-on: ubuntu-latest