EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Restruct gpu_memory_settings in a unify function and relax max_cuda_graph_bs (#10372)

Browse Source 
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: sglang-bot <sglangbot@gmail.com>
This commit is contained in:
Xiaoyu Zhang
2025-09-27 06:10:49 +08:00
committed by GitHub
parent e56c64bfaf
commit 05a3526654
3 changed files with 83 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
.github/workflows/pr-test.yml vendored
View File

@@ -198,7 +198,7 @@ jobs:
strategy:
fail-fast: false
matrix:
part: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
part: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -219,7 +219,7 @@ jobs:
timeout-minutes: 30
run: |
cd test/srt
python3 run_suite.py --suite per-commit --auto-partition-id ${{ matrix.part }} --auto-partition-size 10
python3 run_suite.py --suite per-commit --auto-partition-id ${{ matrix.part }} --auto-partition-size 11
unit-test-backend-2-gpu:
needs: [check-changes, sgl-kernel-build-wheels]
@@ -297,7 +297,7 @@ jobs:
strategy:
fail-fast: false
matrix:
part: [0, 1]
part: [0, 1, 2]
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -318,7 +318,7 @@ jobs:
timeout-minutes: 20
run: |
cd test/srt
python3 run_suite.py --suite per-commit-8-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
python3 run_suite.py --suite per-commit-8-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 3
performance-test-1-gpu-part-1:
needs: [check-changes, sgl-kernel-build-wheels]