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

refactor: rewrite bench-mmmu-sglang (#4458)

Browse Source
This commit is contained in:
Mick
2025-03-18 09:11:47 +08:00
committed by GitHub
parent a98290aea3
commit 98be3bd306
4 changed files with 66 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
benchmark/mmmu/README.md
View File

@@ -3,7 +3,11 @@
### Evaluate sglang
```
python benchmark/mmmu/bench_sglang.py --model-path Qwen/Qwen2-VL-7B-Instruct --chat-template qwen2-vl
python -m sglang.launch_server --model-path Qwen/Qwen2-VL-7B-Instruct --port 30000
```
```
python benchmark/mmmu/bench_sglang.py --model-path Qwen/Qwen2-VL-7B-Instruct --chat-template qwen2-vl --port 30000
```
It's recommended to reduce the memory usage by appending something ike `--mem-fraction-static 0.6` to the command above.