## project link:
https://github.com/ztxz16/fastllm

# Install

## install in linux:

``` sh
# (you should install cuda12 first)
pip install ftllm -U
```

## install in windows

``` sh
pip install https://www.modelscope.cn/models/huangyuyang/fastllmdepend-windows/resolve/master/ftllmdepend-0.0.0.1-py3-none-win_amd64.whl
pip install ftllm -U
```

# Launch

``` sh
ftllm chat YOUR_MODEL_PATH # chat
ftllm webui YOUR_MODEL_PATH # webui
ftllm server YOUR_MODEL_PATH # server 
```