mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 00:57:33 +08:00
Update compile doc
This commit is contained in:
@@ -9,9 +9,10 @@
|
|||||||
|
|
||||||
| 选项 | 作用 | 备注 |
|
| 选项 | 作用 | 备注 |
|
||||||
|:---- | :--- | :--- |
|
|:---- | :--- | :--- |
|
||||||
| ENABLE_ORT_BACKEND | 启用ONNXRuntime推理后端,默认ON | - |
|
| ENABLE_ORT_BACKEND | 启用ONNXRuntime推理后端,默认ON | 默认支持CPU,开启WITH_GPU后,同时支持GPU |
|
||||||
| WITH_GPU | 是否开启GPU使用,默认OFF | 当设为TRUE时,须通过CUDA_DIRECTORY指定cuda目录,如/usr/local/cuda; Mac上不支持设为ON |
|
| ENABLE_PADDLE_BACKEND | 启用Paddle Inference推理后端,默认OFF | 默认支持CPU,开启WITH_GPU后,同时支持GPU |
|
||||||
| ENABLE_TRT_BACKEND | 启用TensorRT推理后端,默认OFF | 当设为TRUE时,需通过TRT_DIRECTORY指定tensorrt目录,如/usr/downloads/TensorRT-8.4.0.1; Mac上不支持设为ON|
|
| ENABLE_TRT_BACKEND | 启用TensorRT推理后端,默认OFF | 仅支持GPU |
|
||||||
| ENABLE_VISION | 编译集成视觉模型模块,包括OpenCV的编译集成,默认OFF | - |
|
| WITH_GPU | 是否开启GPU使用,默认OFF | 当设为TRUE,编译后将支持Nvidia GPU部署 |
|
||||||
| ENABLE_PADDLE_FRONTEND | 编译集成Paddle2ONNX,默认ON | - |
|
| CUDA_DIRECTORY | 指定编译时的CUDA路径,默认为/usr/local/cuda |
|
||||||
| ENABLE_DEBUG | 当为ON时,支持输出DEBUG信息,但可能会有性能损耗,默认OFF | - |
|
| TRT_DIRECTORY | 当启用TensorRT推理后端时,需通过此参数指定TensorRT路径 |
|
||||||
|
| ENABLE_VISION | 启用视觉模型模块,默认为ON |
|
||||||
|
@@ -1,5 +1,13 @@
|
|||||||
# Linux & Mac编译
|
# Linux & Mac编译
|
||||||
|
|
||||||
|
## 环境依赖
|
||||||
|
|
||||||
|
- cmake >= 3.12
|
||||||
|
- g++ >= 8.2
|
||||||
|
- cuda >= 11.2 (当WITH_GPU=ON)
|
||||||
|
- cudnn >= 11.2 (当WITH_GPU=ON)
|
||||||
|
- TensorRT >= 8.4 (当ENABLE_TRT_BACKEND=ON)
|
||||||
|
|
||||||
## 编译C++
|
## 编译C++
|
||||||
```
|
```
|
||||||
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
||||||
@@ -27,4 +35,4 @@ python setup.py bdist_wheel
|
|||||||
```
|
```
|
||||||
编译后的wheel包即在当前目录下的`dist`目录中
|
编译后的wheel包即在当前目录下的`dist`目录中
|
||||||
|
|
||||||
编译选项说明参考[编译指南](./README.md)
|
更多编译选项说明参考[编译指南](./README.md)
|
||||||
|
@@ -1,5 +1,13 @@
|
|||||||
# Windows编译
|
# Windows编译
|
||||||
|
|
||||||
|
## 环境依赖
|
||||||
|
|
||||||
|
- cmake >= 3.12
|
||||||
|
- g++ >= 8.2
|
||||||
|
- cuda >= 11.2 (当WITH_GPU=ON)
|
||||||
|
- cudnn >= 11.2 (当WITH_GPU=ON)
|
||||||
|
- TensorRT >= 8.4 (当ENABLE_TRT_BACKEND=ON)
|
||||||
|
|
||||||
## 获取代码
|
## 获取代码
|
||||||
```
|
```
|
||||||
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
||||||
@@ -34,3 +42,5 @@ set ENABLE_VISION=ON
|
|||||||
python setup.py build
|
python setup.py build
|
||||||
python setup.py bdist_wheel
|
python setup.py bdist_wheel
|
||||||
```
|
```
|
||||||
|
|
||||||
|
更多编译选项说明参考[编译指南](./README.md)
|
||||||
|
Reference in New Issue
Block a user