JQFeng

Results 3 issues of JQFeng

**Please describe the bug** **Please describe the expected behavior** **System information and environment** - OS Platform and Distribution (e.g., Linux Ubuntu 16.04, docker): - Python version: 3.9 - CUDA version:11.3...

I want to know if the parameters in the original `example.json` is reasonable. Or could u give me some recommended parameters? Thanks!

# Problems when use 2 A800 GPU serving LLaMA-3-8B IIRC, no other change besides this. It's ok with one GPU. BTW what's the difference bwtween `actual_gpu_num` and `gpu_num` ![image](https://github.com/user-attachments/assets/0f10520d-3519-4e5c-890d-affa2192fbd4) ![image](https://github.com/user-attachments/assets/0744d6f6-73f3-4336-84c4-ed88861290b9)