ci: run GB300 nightly suite in the standard Nvidia nightly workflow (#28536)

Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
This commit is contained in:
Alison Shao
2026-06-19 12:24:38 -07:00
committed by GitHub
co-authored by Baizhou Zhang Mohammad Miadh Angkad
parent 7c505c2927
commit ab0714d0ee
11 changed files with 72 additions and 197 deletions
+27
View File
@@ -24,6 +24,7 @@ on:
- 'nightly-test-perf-4-gpu-b200'
- 'nightly-test-perf-8-gpu-b200'
- 'nightly-test-specialized-8-gpu-b200'
- 'nightly-test-perf-4-gpu-gb300'
- 'nightly-test-kernel-1-gpu-h100'
- 'nightly-test-diffusion-comparison'
- 'nightly-test-kernel-8-gpu-h200'
@@ -512,6 +513,31 @@ jobs:
- uses: ./.github/actions/upload-cuda-coredumps
if: failure()
# GB300 (Grace-Blackwell NVL4) performance tests - 4 GPU (ARM64)
nightly-test-perf-4-gpu-gb300:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-4-gpu-gb300')
runs-on: 4-gpu-gb300
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.ref || github.ref }}
- uses: ./.github/actions/check-maintenance
- name: Install dependencies
run: |
bash scripts/ci/cuda/ci_install_dependency.sh
- name: Run test
timeout-minutes: 600
run: |
cd test
python3 run_suite.py --hw cuda --suite nightly-4-gpu-gb300 --nightly --continue-on-error --timeout-per-file 7200
- uses: ./.github/actions/upload-cuda-coredumps
if: failure()
# Specialized B200 tests - 8 GPU, for specific backends and configs
nightly-test-specialized-8-gpu-b200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-8-gpu-b200' || inputs.job_filter == 'nightly-test-specialized-8-gpu-b200')
@@ -695,6 +721,7 @@ jobs:
- nightly-test-vlm-perf-2-gpu-h100
- nightly-test-perf-4-gpu-b200
- nightly-test-specialized-8-gpu-b200
- nightly-test-perf-4-gpu-gb300
- nightly-test-diffusion-comparison
- nightly-test-precision-8-gpu-h200
- consolidate-metrics