Update jetson.md

docs/cn/build_and_install/jetson.md

@@ -10,12 +10,17 @@ FastDeploy当前在Jetson仅支持ONNX Runtime CPU和TensorRT GPU两种后端推
 - cmake >= 3.10.0
 - jetpack >= 4.6.1
 
+
+如果需要集成Paddle Inference后端，在[Paddle Inference预编译库](https://www.paddlepaddle.org.cn/inference/v2.4/guides/install/download_lib.html#c)页面根据开发环境选择对应的Jetpack C++包下载，并解压。
+
 ```bash
 git clone https://github.com/PaddlePaddle/FastDeploy.git
 cd FastDeploy
 mkdir build && cd build
 cmake .. -DBUILD_ON_JETSON=ON \
          -DENABLE_VISION=ON \
+         -DENABLE_PADDLE_BACKEND=ON \
+         -DPADDLEINFERENCE_DIRECTORY=/Download/paddle_inference_jetson \
          -DCMAKE_INSTALL_PREFIX=${PWD}/installed_fastdeploy
 make -j8
 make install
@@ -34,6 +39,8 @@ make install
 
 Python打包依赖`wheel`，编译前请先执行`pip install wheel`
 
+如果需要集成Paddle Inference后端，在[Paddle Inference预编译库](https://www.paddlepaddle.org.cn/inference/v2.4/guides/install/download_lib.html#c)页面根据开发环境选择对应的Jetpack C++包下载，并解压。
+
 所有编译选项通过环境变量导入
 
 ```bash
@@ -41,6 +48,8 @@ git clone https://github.com/PaddlePaddle/FastDeploy.git
 cd FastDeploy/python
 export BUILD_ON_JETSON=ON
 export ENABLE_VISION=ON
+export ENABLE_PADDLE_BACKEND=ON
+export PADDLEINFERENCE_DIRECTORY=/Download/paddle_inference_jetson
 
 python setup.py build
 python setup.py bdist_wheel