chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

fix: adding matrix partitioning for h200 and b200 nightly tests (#17091)

Browse Source
This commit is contained in:
Douglas Yang
2026-01-15 11:23:19 -08:00
committed by GitHub
parent 3f44268fe5
commit 655d2c7c2a
11 changed files with 21 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
.github/workflows/nightly-test-nvidia.yml vendored
View File

@@ -98,6 +98,10 @@ jobs:
nightly-test-general-8-gpu-h200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-h200')
runs-on: 8-gpu-h200
strategy:
fail-fast: false
matrix:
partition: [0, 1, 2]
env:
RUNNER_LABELS: 8-gpu-h200
steps:
@@ -120,7 +124,7 @@ jobs:
IS_H200: "1"
run: |
cd test
python3 run_suite.py --hw cuda --suite nightly-8-gpu-common --nightly --timeout-per-file=18000 --continue-on-error
python3 run_suite.py --hw cuda --suite nightly-8-gpu-common --nightly --timeout-per-file=18000 --continue-on-error --auto-partition-id=${{ matrix.partition }} --auto-partition-size=3
- name: Run test
timeout-minutes: 30
@@ -156,8 +160,12 @@ jobs:
# General tests - 8 GPU B200
nightly-test-general-8-gpu-b200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-h20')
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-b200')
runs-on: 8-gpu-b200
strategy:
fail-fast: false
matrix:
partition: [0, 1, 2]
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -177,7 +185,7 @@ jobs:
GPU_CONFIG: "8-gpu-b200"
run: |
cd test
IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite nightly-8-gpu-common --nightly --timeout-per-file=12000 --continue-on-error
IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite nightly-8-gpu-common --nightly --timeout-per-file=12000 --continue-on-error --auto-partition-id=${{ matrix.partition }} --auto-partition-size=3
# Text model accuracy tests
nightly-test-text-accuracy-2-gpu-runner: