diff --git a/docs/compile/how_to_build_windows.md b/docs/compile/how_to_build_windows.md
index 6c293db248..ce4cc2d4a7 100644
--- a/docs/compile/how_to_build_windows.md
+++ b/docs/compile/how_to_build_windows.md
@@ -17,11 +17,11 @@ git clone https://github.com/PaddlePaddle/FastDeploy.git
 cd FastDeploy && git checkout develop
 mkdir build && cd build
 
-cmake .. -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=D:\Paddle\FastDeploy\build\fastdeploy-win-x64-0.2.0 -DENABLE_ORT_BACKEND=ON -DENABLE_PADDLE_BACKEND=ON -DENABLE_VISION=ON -DENABLE_VISION_VISUALIZE=ON
+cmake .. -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=D:\Paddle\FastDeploy\build\fastdeploy-win-x64 -DENABLE_ORT_BACKEND=ON -DENABLE_PADDLE_BACKEND=ON -DENABLE_VISION=ON -DENABLE_VISION_VISUALIZE=ON
 msbuild fastdeploy.sln /m /p:Configuration=Release /p:Platform=x64
 msbuild INSTALL.vcxproj /m /p:Configuration=Release /p:Platform=x64
 ```
-编译后，FastDeploy CPU C++ SDK即在`D:\Paddle\FastDeploy\build\fastdeploy-win-x64-0.2.0`目录下
+编译后，FastDeploy CPU C++ SDK即在`D:\Paddle\FastDeploy\build\fastdeploy-win-x64`目录下
 
 ## 编译GPU版本 C++ SDK
 
@@ -32,7 +32,7 @@ git clone https://github.com/PaddlePaddle/FastDeploy.git
 cd FastDeploy && git checkout develop
 mkdir build && cd build
 
-cmake .. -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=D:\Paddle\FastDeploy\build\fastdeploy-win-x64-gpu-0.2.0 -DWITH_GPU=ON -DENABLE_ORT_BACKEND=ON -DENABLE_PADDLE_BACKEND=ON -DENABLE_VISION=ON -DENABLE_VISION_VISUALIZE=ON -DCUDA_DIRECTORY="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2"
+cmake .. -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=D:\Paddle\FastDeploy\build\fastdeploy-win-x64-gpu -DWITH_GPU=ON -DENABLE_ORT_BACKEND=ON -DENABLE_PADDLE_BACKEND=ON -DENABLE_VISION=ON -DENABLE_VISION_VISUALIZE=ON -DCUDA_DIRECTORY="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2"
 msbuild fastdeploy.sln /m /p:Configuration=Release /p:Platform=x64
 msbuild INSTALL.vcxproj /m /p:Configuration=Release /p:Platform=x64  
 
@@ -42,7 +42,7 @@ msbuild INSTALL.vcxproj /m /p:Configuration=Release /p:Platform=x64
 % (3) 若编译TensorRT后端，需要设置-DENABLE_TRT_BACKEND=ON，并指定TRT_DIRECTORY %
 % (4) 如-DTRT_DIRECTORY=D:\x64\third_party\TensorRT-8.4.1.5 %
 ```
-编译后，FastDeploy GPU C++ SDK即在`D:\Paddle\FastDeploy\build\fastdeploy-win-x64-gpu-0.2.0`目录下
+编译后，FastDeploy GPU C++ SDK即在`D:\Paddle\FastDeploy\build\fastdeploy-win-x64-gpu`目录下
 
 ## 编译CPU版本 Python Wheel包
 
@@ -62,7 +62,7 @@ C:\Python38\python.exe setup.py bdist_wheel
 ```
 编译好的wheel文件在dist目录下，pip安装编译好的wheel包，命令如下
 ```bat
-C:\Python38\python.exe -m pip install dist\fastdeploy_python-0.2.0-cp38-cp38-win_amd64.whl
+C:\Python38\python.exe -m pip install dist\fastdeploy_python-0.2.1-cp38-cp38-win_amd64.whl
 ```
 
 ## 编译GPU版本 Python Wheel包  
@@ -89,6 +89,6 @@ C:\Python38\python.exe setup.py bdist_wheel
 ```
 编译好的wheel文件在dist目录下，pip安装编译好的wheel包，命令如下
 ```bat
-C:\Python38\python.exe -m pip install dist\fastdeploy_gpu_python-0.2.0-cp38-cp38-win_amd64.whl
+C:\Python38\python.exe -m pip install dist\fastdeploy_gpu_python-0.2.1-cp38-cp38-win_amd64.whl
 ```
 更多编译选项说明参考[编译指南](./README.md)
diff --git a/docs/compile/how_to_use_sdk_on_windows.md b/docs/compile/how_to_use_sdk_on_windows.md
index 47b6185a04..b69d076842 100644
--- a/docs/compile/how_to_use_sdk_on_windows.md
+++ b/docs/compile/how_to_use_sdk_on_windows.md
@@ -18,7 +18,7 @@
 ## 下载 FastDeploy Windows 10 C++ SDK
 可以从以下链接下载编译好的 FastDeploy Windows 10 C++ SDK，SDK中包含了examples代码。
 ```text
-https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-gpu-0.2.0.zip
+https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-gpu-0.2.1.zip
 ```
 ## 准备模型文件和测试图片  
 可以从以下链接下载模型文件和测试图片，并解压缩
@@ -34,7 +34,7 @@ cd fastdeploy-win-x64-gpu-0.2.0\examples\vision\detection\paddledetection\cpp
 ```
 ```bat
 mkdir build && cd build
-cmake .. -G "Visual Studio 16 2019" -A x64 -DFASTDEPLOY_INSTALL_DIR=%cd%\..\..\..\..\..\..\..\fastdeploy-win-x64-gpu-0.2.0 -DCUDA_DIRECTORY="C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v11.2"
+cmake .. -G "Visual Studio 16 2019" -A x64 -DFASTDEPLOY_INSTALL_DIR=%cd%\..\..\..\..\..\..\..\fastdeploy-win-x64-gpu-0.2.1 -DCUDA_DIRECTORY="C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v11.2"
 ```
 然后执行
 ```bat
@@ -44,7 +44,7 @@ msbuild infer_demo.sln /m:4 /p:Configuration=Release /p:Platform=x64
 #### 方式一：命令行设置环境变量
 编译好的exe保存在Release目录下，在运行demo前，需要将模型和测试图片拷贝至该目录。另外，需要在终端指定DLL的搜索路径。请在build目录下执行以下命令。
 ```bat
-set FASTDEPLOY_PATH=%cd%\..\..\..\..\..\..\..\fastdeploy-win-x64-gpu-0.2.0
+set FASTDEPLOY_PATH=%cd%\..\..\..\..\..\..\..\fastdeploy-win-x64-gpu-0.2.1
 set PATH=%FASTDEPLOY_PATH%\lib;%FASTDEPLOY_PATH%\third_libs\install\onnxruntime\lib;%FASTDEPLOY_PATH%\third_libs\install\opencv-win-x64-3.4.16\build\x64\vc15\bin;%FASTDEPLOY_PATH%\third_libs\install\paddle_inference\paddle\lib;%FASTDEPLOY_PATH%\third_libs\install\paddle_inference\third_party\install\mkldnn\lib;%FASTDEPLOY_PATH%\third_libs\install\paddle_inference\third_party\install\mklml\lib;%FASTDEPLOY_PATH%\third_libs\install\paddle2onnx\lib;%FASTDEPLOY_PATH%\third_libs\install\tensorrt\lib;%FASTDEPLOY_PATH%\third_libs\install\yaml-cpp\lib;%PATH%
 ```
 注意，需要拷贝onnxruntime.dll到exe所在的目录。
@@ -59,7 +59,7 @@ C:\Windows\System32\onnxruntime.dll  # windows自带的onnxruntime.dll
 #### 方式二：拷贝依赖库到exe的目录下
 手动拷贝，或者在build目录下执行以下命令：
 ```bat
-set FASTDEPLOY_PATH=%cd%\..\..\..\..\..\..\..\fastdeploy-win-x64-gpu-0.2.0
+set FASTDEPLOY_PATH=%cd%\..\..\..\..\..\..\..\fastdeploy-win-x64-gpu-0.2.1
 copy /Y %FASTDEPLOY_PATH%\lib\*.dll Release\
 copy /Y %FASTDEPLOY_PATH%\third_libs\install\onnxruntime\lib\*.dll Release\
 copy /Y %FASTDEPLOY_PATH%\third_libs\install\opencv-win-x64-3.4.16\build\x64\vc15\bin\*.dll Release\
diff --git a/docs/docs_en/compile/how_to_build_windows.md b/docs/docs_en/compile/how_to_build_windows.md
index c25095c1e7..2351125ca2 100644
--- a/docs/docs_en/compile/how_to_build_windows.md
+++ b/docs/docs_en/compile/how_to_build_windows.md
@@ -17,12 +17,12 @@ git clone https://github.com/PaddlePaddle/FastDeploy.git
 cd FastDeploy && git checkout develop
 mkdir build && cd build
 
-cmake .. -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=D:\Paddle\FastDeploy\build\fastdeploy-win-x64-0.2.0 -DENABLE_ORT_BACKEND=ON -DENABLE_PADDLE_BACKEND=ON -DENABLE_VISION=ON -DENABLE_VISION_VISUALIZE=ON
+cmake .. -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=D:\Paddle\FastDeploy\build\fastdeploy-win-x64-0.2.1-DENABLE_ORT_BACKEND=ON -DENABLE_PADDLE_BACKEND=ON -DENABLE_VISION=ON -DENABLE_VISION_VISUALIZE=ON
 msbuild fastdeploy.sln /m /p:Configuration=Release /p:Platform=x64
 msbuild INSTALL.vcxproj /m /p:Configuration=Release /p:Platform=x64
 ```
 
-After compilation, the FastDeploy CPU C++ SDK is in the `D:\Paddle\FastDeploy\build\fastdeploy-win-x64-0.2.0` directory
+After compilation, the FastDeploy CPU C++ SDK is in the `D:\Paddle\FastDeploy\build\fastdeploy-win-x64-0.2.1` directory
 
 ## Compile C++ SDK for GPU
 
@@ -33,7 +33,7 @@ git clone https://github.com/PaddlePaddle/FastDeploy.git
 cd FastDeploy && git checkout develop
 mkdir build && cd build
 
-cmake .. -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=D:\Paddle\FastDeploy\build\fastdeploy-win-x64-gpu-0.2.0 -DWITH_GPU=ON -DENABLE_ORT_BACKEND=ON -DENABLE_PADDLE_BACKEND=ON -DENABLE_VISION=ON -DENABLE_VISION_VISUALIZE=ON -DCUDA_DIRECTORY="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2"
+cmake .. -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=D:\Paddle\FastDeploy\build\fastdeploy-win-x64-gpu-0.2.1 -DWITH_GPU=ON -DENABLE_ORT_BACKEND=ON -DENABLE_PADDLE_BACKEND=ON -DENABLE_VISION=ON -DENABLE_VISION_VISUALIZE=ON -DCUDA_DIRECTORY="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2"
 msbuild fastdeploy.sln /m /p:Configuration=Release /p:Platform=x64
 msbuild INSTALL.vcxproj /m /p:Configuration=Release /p:Platform=x64  
 
diff --git a/docs/docs_en/quick_start/install_cpp_sdk.md b/docs/docs_en/quick_start/install_cpp_sdk.md
index 7fb691f7d9..15c0caf6be 100644
--- a/docs/docs_en/quick_start/install_cpp_sdk.md
+++ b/docs/docs_en/quick_start/install_cpp_sdk.md
@@ -14,15 +14,15 @@ FastDeploy provides prebuilt CPP deployment libraries on Windows/Linux/Mac. Deve
 
 | SDK Download Link                                                                                                 | Hardware | Description                              |
 |:--------------------------------------------------------------------------------------------------------------------- |:-------- |:---------------------------------------- |
-| [fastdeploy-linux-x64-0.2.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz)         | CPU      | Built with g++ 8.2                       |
-| [fastdeploy-linux-x64-gpu-0.2.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz) | CPU/GPU  | Built with g++ 8.2, cuda 11.2, cudnn 8.2 |
+| [fastdeploy-linux-x64-0.2.1.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz)         | CPU      | Built with g++ 8.2                       |
+| [fastdeploy-linux-x64-gpu-0.2.1.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz) | CPU/GPU  | Built with g++ 8.2, cuda 11.2, cudnn 8.2 |
 
 ### Windows 10 x64
 
 | SDK Download Link                                                                                             | Hardware | Description                                           |
 |:----------------------------------------------------------------------------------------------------------------- |:-------- |:----------------------------------------------------- |
-| [fastdeploy-win-x64-0.2.0.zip](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-0.2.0.zip)         | CPU      | Built with Visual Studio 16 2019                      |
-| [fastdeploy-win-x64-gpu-0.2.0.zip](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-gpu-0.2.0.zip) | CPU/GPU  | Built with Visual Studio 16 2019，cuda 11.2, cudnn 8.2 |
+| [fastdeploy-win-x64-0.2.1.zip](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-0.2.1.zip)         | CPU      | Built with Visual Studio 16 2019                      |
+| [fastdeploy-win-x64-gpu-0.2.1.zip](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-gpu-0.2.1.zip) | CPU/GPU  | Built with Visual Studio 16 2019，cuda 11.2, cudnn 8.2 |
 
 ### Linux aarch64
 
@@ -35,8 +35,8 @@ FastDeploy provides prebuilt CPP deployment libraries on Windows/Linux/Mac. Deve
 
 | SDK Download Link                                                                                            | Architecture | Hardware |
 |:--------------------------------------------------------------------------------------------------------------- |:------------ |:-------- |
-| [fastdeploy-osx-x86_64-0.2.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-osx-x86_64-0.2.0.tgz) | x86          | CPU      |
-| [fastdeploy-osx-arm64-0.2.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-osx-arm64-0.2.0.tgz)   | arm64        | CPU      |
+| [fastdeploy-osx-x86_64-0.2.1.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-osx-x86_64-0.2.1.tgz) | x86          | CPU      |
+| [fastdeploy-osx-arm64-0.2.1.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-osx-arm64-0.2.1.tgz)   | arm64        | CPU      |
 
 ## Other related docs
 
diff --git a/docs/quick_start/CPP_prebuilt_libraries.md b/docs/quick_start/CPP_prebuilt_libraries.md
index 8878f3115e..af047006cf 100644
--- a/docs/quick_start/CPP_prebuilt_libraries.md
+++ b/docs/quick_start/CPP_prebuilt_libraries.md
@@ -14,8 +14,8 @@ FastDeploy提供了在Windows/Linux/Mac上的预先编译CPP部署库，开发
 
 | 部署库下载地址 | 硬件 | 说明 |
 | :------------- | :--- | :--- |
-| [fastdeploy-linux-x64-0.2.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz) | CPU | g++ 8.2编译产出 |
-| [fastdeploy-linux-x64-gpu-0.2.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz) | CPU/GPU | g++ 8.2, cuda 11.2, cudnn 8.2编译产出 |
+| [fastdeploy-linux-x64-0.2.1.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz) | CPU | g++ 8.2编译产出 |
+| [fastdeploy-linux-x64-gpu-0.2.1.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz) | CPU/GPU | g++ 8.2, cuda 11.2, cudnn 8.2编译产出 |
 
 ### Windows 10 x64平台
 
diff --git a/examples/vision/classification/paddleclas/cpp/README.md b/examples/vision/classification/paddleclas/cpp/README.md
index 27dccaab88..6a91a24a77 100644
--- a/examples/vision/classification/paddleclas/cpp/README.md
+++ b/examples/vision/classification/paddleclas/cpp/README.md
@@ -11,12 +11,12 @@
 
 ```bash
 #下载SDK，编译模型examples代码（SDK中包含了examples代码）
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-gpu-0.2.0.tgz
-cd fastdeploy-linux-x64-gpu-0.2.0/examples/vision/classification/paddleclas/cpp
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-gpu-0.2.1.tgz
+cd fastdeploy-linux-x64-gpu-0.2.1/examples/vision/classification/paddleclas/cpp
 mkdir build
 cd build
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.2.0
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.2.1
 make -j
 
 # 下载ResNet50_vd模型文件和测试图片
diff --git a/examples/vision/detection/nanodet_plus/cpp/README.md b/examples/vision/detection/nanodet_plus/cpp/README.md
index 71a37a92b4..90291620c0 100644
--- a/examples/vision/detection/nanodet_plus/cpp/README.md
+++ b/examples/vision/detection/nanodet_plus/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的NanoDetPlus模型文件和测试图片
diff --git a/examples/vision/detection/paddledetection/cpp/README.md b/examples/vision/detection/paddledetection/cpp/README.md
index f34a64d166..99d3844713 100644
--- a/examples/vision/detection/paddledetection/cpp/README.md
+++ b/examples/vision/detection/paddledetection/cpp/README.md
@@ -13,11 +13,11 @@
 以ppyoloe为例进行推理部署
 
 #下载SDK，编译模型examples代码（SDK中包含了examples代码）
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-gpu-0.2.0.tgz
-cd fastdeploy-linux-x64-gpu-0.2.0/examples/vision/detection/paddledetection/cpp
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-gpu-0.2.1.tgz
+cd fastdeploy-linux-x64-gpu-0.2.1/examples/vision/detection/paddledetection/cpp
 mkdir build && cd build
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.2.0
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.2.1
 make -j
 
 # 下载PPYOLOE模型文件和测试图片
diff --git a/examples/vision/detection/scaledyolov4/cpp/README.md b/examples/vision/detection/scaledyolov4/cpp/README.md
index 6bf3a5e7b4..6b9959f029 100644
--- a/examples/vision/detection/scaledyolov4/cpp/README.md
+++ b/examples/vision/detection/scaledyolov4/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的ScaledYOLOv4模型文件和测试图片
diff --git a/examples/vision/detection/yolor/cpp/README.md b/examples/vision/detection/yolor/cpp/README.md
index 4564c78b74..20195aba88 100644
--- a/examples/vision/detection/yolor/cpp/README.md
+++ b/examples/vision/detection/yolor/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的YOLOR模型文件和测试图片
diff --git a/examples/vision/detection/yolov5/cpp/README.md b/examples/vision/detection/yolov5/cpp/README.md
index 67dfa4a106..1b261dba99 100644
--- a/examples/vision/detection/yolov5/cpp/README.md
+++ b/examples/vision/detection/yolov5/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的yolov5模型文件和测试图片
diff --git a/examples/vision/detection/yolov5lite/cpp/README.md b/examples/vision/detection/yolov5lite/cpp/README.md
index df889b6d21..6d1dfc9190 100644
--- a/examples/vision/detection/yolov5lite/cpp/README.md
+++ b/examples/vision/detection/yolov5lite/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的YOLOv5Lite模型文件和测试图片
diff --git a/examples/vision/detection/yolov6/cpp/README.md b/examples/vision/detection/yolov6/cpp/README.md
index b335ad068c..90d93ea6f4 100644
--- a/examples/vision/detection/yolov6/cpp/README.md
+++ b/examples/vision/detection/yolov6/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的YOLOv6模型文件和测试图片
diff --git a/examples/vision/detection/yolov7/cpp/README.md b/examples/vision/detection/yolov7/cpp/README.md
index 02137cd2b1..21ab4d31a5 100644
--- a/examples/vision/detection/yolov7/cpp/README.md
+++ b/examples/vision/detection/yolov7/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的yolov7模型文件和测试图片
diff --git a/examples/vision/detection/yolov7end2end_ort/cpp/README.md b/examples/vision/detection/yolov7end2end_ort/cpp/README.md
index d502898e83..476b552206 100644
--- a/examples/vision/detection/yolov7end2end_ort/cpp/README.md
+++ b/examples/vision/detection/yolov7end2end_ort/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-gpu-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-gpu-0.2.1
 make -j
 # 如果预编译库还没有支持该模型，请从develop分支源码编译最新的SDK
 
diff --git a/examples/vision/detection/yolov7end2end_trt/cpp/README.md b/examples/vision/detection/yolov7end2end_trt/cpp/README.md
index 8667341f66..b7e725a1da 100644
--- a/examples/vision/detection/yolov7end2end_trt/cpp/README.md
+++ b/examples/vision/detection/yolov7end2end_trt/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-gpu-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-gpu-0.2.1
 make -j
 # 若预编译库没有支持该类 则请自行从源码develop分支编译最新的FastDeploy C++ SDK
 
diff --git a/examples/vision/detection/yolox/cpp/README.md b/examples/vision/detection/yolox/cpp/README.md
index 7523d6582f..a1b10d0bcd 100644
--- a/examples/vision/detection/yolox/cpp/README.md
+++ b/examples/vision/detection/yolox/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的YOLOX模型文件和测试图片
diff --git a/examples/vision/facedet/retinaface/cpp/README.md b/examples/vision/facedet/retinaface/cpp/README.md
index 6a4702ba68..85feee82bf 100644
--- a/examples/vision/facedet/retinaface/cpp/README.md
+++ b/examples/vision/facedet/retinaface/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的RetinaFace模型文件和测试图片
diff --git a/examples/vision/facedet/scrfd/cpp/README.md b/examples/vision/facedet/scrfd/cpp/README.md
index a7cb17ff51..850cf61cd4 100644
--- a/examples/vision/facedet/scrfd/cpp/README.md
+++ b/examples/vision/facedet/scrfd/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的SCRFD模型文件和测试图片
diff --git a/examples/vision/facedet/ultraface/cpp/README.md b/examples/vision/facedet/ultraface/cpp/README.md
index c9fba788ea..0b0d8d389a 100644
--- a/examples/vision/facedet/ultraface/cpp/README.md
+++ b/examples/vision/facedet/ultraface/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的UltraFace模型文件和测试图片
diff --git a/examples/vision/facedet/yolov5face/cpp/README.md b/examples/vision/facedet/yolov5face/cpp/README.md
index 518bf77971..a99c51ff3c 100644
--- a/examples/vision/facedet/yolov5face/cpp/README.md
+++ b/examples/vision/facedet/yolov5face/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的YOLOv5Face模型文件和测试图片
diff --git a/examples/vision/faceid/insightface/cpp/README.md b/examples/vision/faceid/insightface/cpp/README.md
index 7ea48bac5f..b402db1ada 100644
--- a/examples/vision/faceid/insightface/cpp/README.md
+++ b/examples/vision/faceid/insightface/cpp/README.md
@@ -12,9 +12,9 @@
 ```bash
 mkdir build
 cd build
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的ArcFace模型文件和测试图片
diff --git a/examples/vision/matting/modnet/cpp/README.md b/examples/vision/matting/modnet/cpp/README.md
index ea6d243b82..a5d9d16608 100644
--- a/examples/vision/matting/modnet/cpp/README.md
+++ b/examples/vision/matting/modnet/cpp/README.md
@@ -10,11 +10,11 @@
 以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试
 
 ```bash
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
 
 mkdir build && cd build
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 #下载官方转换好的MODNet模型文件和测试图片
diff --git a/examples/vision/matting/ppmatting/cpp/README.md b/examples/vision/matting/ppmatting/cpp/README.md
index 4d79bcde83..93e87f2e3e 100644
--- a/examples/vision/matting/ppmatting/cpp/README.md
+++ b/examples/vision/matting/ppmatting/cpp/README.md
@@ -11,11 +11,11 @@
 
 ```bash
 #下载SDK，编译模型examples代码（SDK中包含了examples代码）
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-gpu-0.2.0.tgz
-cd fastdeploy-linux-x64-gpu-0.2.0/examples/vision/matting/ppmatting/cpp/
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-gpu-0.2.1.tgz
+cd fastdeploy-linux-x64-gpu-0.2.1/examples/vision/matting/ppmatting/cpp/
 mkdir build && cd build
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.2.0
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.2.1
 make -j
 
 # 下载PPMatting模型文件和测试图片
diff --git a/examples/vision/ocr/PPOCRSystemv2/cpp/README.md b/examples/vision/ocr/PPOCRSystemv2/cpp/README.md
index 2c4aae5fc6..777fdcb3ee 100644
--- a/examples/vision/ocr/PPOCRSystemv2/cpp/README.md
+++ b/examples/vision/ocr/PPOCRSystemv2/cpp/README.md
@@ -12,9 +12,9 @@
 ```
 mkdir build
 cd build
-wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 
diff --git a/examples/vision/ocr/PPOCRSystemv3/cpp/README.md b/examples/vision/ocr/PPOCRSystemv3/cpp/README.md
index 141b3c013e..8836e36e76 100644
--- a/examples/vision/ocr/PPOCRSystemv3/cpp/README.md
+++ b/examples/vision/ocr/PPOCRSystemv3/cpp/README.md
@@ -12,9 +12,9 @@
 ```
 mkdir build
 cd build
-wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-0.2.0.tgz
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
+wget https://https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-0.2.1.tgz
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.1
 make -j
 
 
diff --git a/examples/vision/segmentation/paddleseg/cpp/README.md b/examples/vision/segmentation/paddleseg/cpp/README.md
index 345a708e85..5d8d785cc7 100644
--- a/examples/vision/segmentation/paddleseg/cpp/README.md
+++ b/examples/vision/segmentation/paddleseg/cpp/README.md
@@ -10,12 +10,12 @@
 以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试
 
 ```bash
-wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
-tar xvf fastdeploy-linux-x64-gpu-0.2.0.tgz
-cd fastdeploy-linux-x64-gpu-0.2.0/examples/vision/segmentation/paddleseg/cpp/
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.1.tgz
+tar xvf fastdeploy-linux-x64-gpu-0.2.1.tgz
+cd fastdeploy-linux-x64-gpu-0.2.1/examples/vision/segmentation/paddleseg/cpp/
 mkdir build
 cd build
-cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.2.0
+cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.2.1
 make -j
 
 # 下载Unet模型文件和测试图片