GitLab

* [Fix] fix issue 127

* 优化防止接口更改

* 如果没有deepspeed用python启动需要手动加载到GPU上

* rollback the changes about max_out_tokens and delelte torch > 2.0 if statement

* support kernel injection with customized deepspeed

* spelling error

* Update chat.py

---------
Co-authored-by: wangruohui <12756472+wangruohui@users.noreply.github.com>