lm-sys/FastChat

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

Open

#1,248 建立於 2023年5月15日

在 GitHub 查看
 (2 留言) (0 反應) (0 負責人)Python (38,959 star) (4,736 fork)batch import
buggood first issue

描述

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"

貢獻者指南

技術棧
python
領域
backendmachine learning
議題類型
bug
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
2
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
1-3 hours
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
fresh
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
Basic PythonUnderstanding of CUDA GPU management
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
40
研究方向
The issue is in fastchat/model/rwkv model.py where the strategy is hardcoded as 'cuda fp16'. The model worker command line arguments num gpus and gpus are not being used to set the strategy accordingly. The fix should parse these arguments and construct a strategy string that specifies which GPUs to use, e.g., 'cuda:0 fp16 > cuda:1 fp16'. Refer to the model worker's argument parsing in fastchat/serve/model worker.py and the existing GPU allocation logic.