mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
[LLM] Add output module and polish docs
This commit is contained in:
10
README.md
10
README.md
@@ -31,22 +31,26 @@ FastDeploy升级2.0版本支持多种大模型推理(当前仅支持Qwen2,
|
||||
|
||||
## 安装
|
||||
|
||||
推荐使用Docker安装
|
||||
### Docker安装(推荐)
|
||||
```
|
||||
docker pull iregistry.baidu-int.com/paddlepaddle/fastdeploy:2.0.0-alpha
|
||||
```
|
||||
|
||||
### 源码安装
|
||||
1. 安装PaddlePaddle GPU(nightly build,代码版本需新于2025.05.30),详见[PaddlePaddle安装](https://www.paddlepaddle.org.cn/en/install/quick?docurl=/documentation/docs/en/develop/install/pip/linux-pip_en.html),指定安装CUDA 12.6 develop(Nightly build)版本,如下命令可完成安装
|
||||
#### 安装PaddlePaddle
|
||||
> 注意安装nightly build版本,代码版本需新于2025.05.30,详见[PaddlePaddle安装](https://www.paddlepaddle.org.cn/en/install/quick?docurl=/documentation/docs/en/develop/install/pip/linux-pip_en.html),指定安装CUDA 12.6 develop(Nightly build)版本。
|
||||
```
|
||||
python -m pip install --pre paddlepaddle-gpu -i https://www.paddlepaddle.org.cn/packages/nightly/cu126/
|
||||
```
|
||||
|
||||
2. 安装FastDeploy
|
||||
#### 编译安装FastDeploy
|
||||
|
||||
```
|
||||
# 编译
|
||||
cd FastDeploy
|
||||
bash build.sh
|
||||
# 安装
|
||||
pip install dist/fastdeploy-2.0.0a0-py3-none-any.whl
|
||||
```
|
||||
|
||||
## 快速使用
|
||||
|
||||
Reference in New Issue
Block a user