[Bug]: Qwen2-VL-7B with sglang (vLLM-back) Performance Degradation on MME benchmark #10588
Open
1 task done
Labels
bug
Something isn't working
Your current environment
This issue has been raised here. Please have a look.
sgl-project/sglang#2112
Model Input Dumps
This issue has been raised here. Please have a look.
sgl-project/sglang#2112
🐛 Describe the bug
This issue has been raised here. Please have a look.
sgl-project/sglang#2112
Before submitting a new issue...
The text was updated successfully, but these errors were encountered: