Files
sglang/benchmark/mmmu/README.md
Ravi Theja 7d9679b74d Add MMMU benchmark results (#4491)
Co-authored-by: Ravi Theja Desetty <ravitheja@Ravis-MacBook-Pro.local>
2025-04-25 15:23:53 +08:00

24 lines
464 B
Markdown

## Run evaluation
### Evaluate sglang
Host the VLM:
```
python -m sglang.launch_server --model-path Qwen/Qwen2-VL-7B-Instruct --chat-template qwen2-vl --port 30000
```
Benchmark:
```
python benchmark/mmmu/bench_sglang.py --port 30000
```
It's recommended to reduce the memory usage by appending something ike `--mem-fraction-static 0.6` to the command above.
### Evaluate hf
```
python benchmark/mmmu/bench_hf.py --model-path Qwen/Qwen2-VL-7B-Instruct
```