lm-sys/FastChat

[BUG] RWKV Models are not configured to use Cuda GPU lists.

Aberta

#1.248 aberto em 15 de mai. de 2023

 (2 comentários) (0 reação) (0 responsável)Python (4.736 forks)batch import
buggood first issue

Métricas do repositório

Stars
 (38.959 estrelas)
Métricas de merge de PR
 (Métricas PR pendentes)

Description

Hello,

The file (fastchat/model/rwkv_model.py) has a RWKV stratergy (strategy="cuda fp16") being set that is not imlemented to use the native --gpus or --num-gpus fschat command arguments.

Example, Launching a model worker with (--num-gpus 4 --gpus 0,1,2,3) does not spawn the RWKV instance with these GPU specifications and just uses GPU 1

strategy="cuda fp16"

VS.

strategy="cuda:0 fp16 -> cuda:1 fp16 -> cuda:2 fp16 -> cuda:3 fp16 -> cuda:4 fp16"

Guia do colaborador