Xu Huang

> I meet the same error. And I try the setting as @Louis-J metioned but it couldn't solve the problem. Even more, I try to set `trial_gpu_number` as 9 and...

Is there any solutions to the problem? I need the similar feature in my model training loop, where `Ctrl`+`C` is used as a stop signal for all processes. And then...

Hi, have you tested the new version in multi-gpu environment? I tried it with below command: ```shell CUDA_VISIBLE_DEVICES=0,1 python3 -m fastchat.serve.vllm_worker --model-path /path/to/Meta-Llama-3-8B-Instruct --dtype float16 --model-names gpt-3.5-turbo-0613 --conv-template llama-3 --lora-dtype...

I have the same confusion, looking forward to the inference file with prompt~ @liminghao1630

 Here is a dataset from @pepsi2222.

Because the user_hist passed to tst_data contains the interactions in val_data, we pass it to test data only because when evaluation on test data, we need to use interactions in...

> Apologize for the long delay. Will definitely take a look after the ICLR deadline. Thanks! Good luck with your submission~

I have the same issue occasionally, any solutions? Here is my exception traceback: ``` ERROR: Exception in ASGI application Traceback (most recent call last): File "/home/ma-user/anaconda3/envs/fschat/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 408, in run_asgi...