lm-sys/FastChat

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

Open

#1 248 ouverte le 15 mai 2023

Voir sur GitHub
 (2 commentaires) (0 réactions) (0 assignés)Python (4 736 forks)batch import
buggood first issue

Métriques du dépôt

Stars
 (38 959 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

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"

Guide contributeur