Lyu Han

16G是不够的。LMDeploy按理说要报 OOM 才对。 @irexyc 总感觉 lmdeploy 在 windows 上磕磕绊绊的，跟进下吧。

@vody-am If you are familiar with Chinese, could you please update the user guide in `docs/zh_cn/serving/api_server_vl.md`?

Yes, by setting `tp` parameter

Hi, @vody-am there are linting errors, which are able to fixed by running the following commands: ``` pip install pre-commit cd the/root/path/of/lmdeploy pre-commit install . pre-commit run --all-files ```

@vansin 帮忙建立 lmdeploy 专门的用户群吧

> @irexyc @lvhan028 两位前辈，顺带一提，lmdeploy什么时候可以像xtuner一样有一个自己的交流群呀（而不是使用internlm2的... 已经创建好了。readme中webchat链接有二维码

``` urllib3.exceptions.ProxyError: ('Unable to connect to proxy', SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:1129)'))) ``` It looks like downloading the model failed. Try to download the model manually and...

@irexyc May provide a best practice guide on windows platform

LMDeploy is developed on CUDA platform. It cannot support MacOS

操作系统是什么？