本地部署后，运行很慢啊

QwenLM / Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Apache License 2.0

12.47k stars 1.01k forks source link

本地部署后，运行很慢啊 #1245

Closed wangwm closed 1 month ago

wangwm commented 1 month ago

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

[X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

[X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

本地部署后，cpu和磁盘占用率过高。chatbot聊天 1分钟出一个字。什么原因啊？

3a424b2d0de57970872103881be2148

1asdasdasda commented 1 month ago

你模型使用的是哪个？可以看一下GPU的显存使用情况。感觉你部署的使用的是CPU.所以感觉很慢。

wangwm commented 1 month ago

直接 git clone https://github.com/QwenLM/Qwen-7B.git 。不知道是哪个版本，我的显卡是rtx3060 ，没被使用。磁盘io非常高

1asdasdasda commented 1 month ago

我是使用的docker部署的。没有直接clone代码。可以使用Ollama部署Qwen模型，挺方便的

jklj077 commented 1 month ago

As Qwen1.0 is no longer actively maintained, we kindly ask to you migrate to Qwen1.5 and direct your related question there. Thanks for you cooperation.