提交 978876c7 编写于 作者: W wangjiawei04

fix

上级 3567c9e5
...@@ -136,7 +136,7 @@ The url corresponding to `cuda9.0_cudnn7-mkl`, copy it and run ...@@ -136,7 +136,7 @@ The url corresponding to `cuda9.0_cudnn7-mkl`, copy it and run
pip install https://paddle-wheel.bj.bcebos.com/2.0.0-gpu-cuda9-cudnn7-mkl/paddlepaddle_gpu-2.0.0.post90-cp27-cp27mu-linux_x86_64.whl pip install https://paddle-wheel.bj.bcebos.com/2.0.0-gpu-cuda9-cudnn7-mkl/paddlepaddle_gpu-2.0.0.post90-cp27-cp27mu-linux_x86_64.whl
``` ```
the default `paddlepaddle-gpu==2.0.0` is Cuda 10.2 with no TensorRT. If you want to install PaddlePaddle with TensorRT. please also check the documentation-multi-version whl package list and find key word `cuda10.2-cudnn8.0-trt7.1.3` the default `paddlepaddle-gpu==2.0.0` is Cuda 10.2 with no TensorRT. If you want to install PaddlePaddle with TensorRT. please also check the documentation-multi-version whl package list and find key word `cuda10.2-cudnn8.0-trt7.1.3`. More info please check [Paddle Serving uses TensorRT](./doc/TENSOR_RT.md)
If it is other environment and Python version, please find the corresponding link in the table and install it with pip. If it is other environment and Python version, please find the corresponding link in the table and install it with pip.
...@@ -223,6 +223,7 @@ the response is ...@@ -223,6 +223,7 @@ the response is
- [Develop Pipeline Serving](doc/PIPELINE_SERVING.md) - [Develop Pipeline Serving](doc/PIPELINE_SERVING.md)
- [Deploy Web Service with uWSGI](doc/UWSGI_DEPLOY.md) - [Deploy Web Service with uWSGI](doc/UWSGI_DEPLOY.md)
- [Hot loading for model file](doc/HOT_LOADING_IN_SERVING.md) - [Hot loading for model file](doc/HOT_LOADING_IN_SERVING.md)
- [Paddle Serving uses TensorRT](doc/TENSOR_RT.md)
### About Efficiency ### About Efficiency
- [How to profile Paddle Serving latency?](python/examples/util) - [How to profile Paddle Serving latency?](python/examples/util)
......
...@@ -112,7 +112,7 @@ pip install paddle-serving-server-gpu==0.5.0.post11 # GPU with CUDA10.1 + Tensor ...@@ -112,7 +112,7 @@ pip install paddle-serving-server-gpu==0.5.0.post11 # GPU with CUDA10.1 + Tensor
您可能需要使用国内镜像源(例如清华源, 在pip命令中添加`-i https://pypi.tuna.tsinghua.edu.cn/simple`)来加速下载。 您可能需要使用国内镜像源(例如清华源, 在pip命令中添加`-i https://pypi.tuna.tsinghua.edu.cn/simple`)来加速下载。
如果需要使用develop分支编译的安装包,请从[最新安装包列表](./doc/LATEST_PACKAGES.md)中获取下载地址进行下载,使用`pip install`命令进行安装。如果您想自行编译,请参照[Paddle Serving编译文档](./doc/COMPILE_CN.md) 如果需要使用develop分支编译的安装包,请从[最新安装包列表](./doc/LATEST_PACKAGES.md)中获取下载地址进行下载,使用`pip install`命令进行安装。如果您想自行编译,请参照[Paddle Serving编译文档](./doc/COMPILE_CN.md)
paddle-serving-server和paddle-serving-server-gpu安装包支持Centos 6/7, Ubuntu 16/18和Windows 10。 paddle-serving-server和paddle-serving-server-gpu安装包支持Centos 6/7, Ubuntu 16/18和Windows 10。
...@@ -134,7 +134,7 @@ pip install paddlepaddle-gpu==2.0.0 ...@@ -134,7 +134,7 @@ pip install paddlepaddle-gpu==2.0.0
``` ```
pip install https://paddle-wheel.bj.bcebos.com/2.0.0-gpu-cuda9-cudnn7-mkl/paddlepaddle_gpu-2.0.0.post90-cp27-cp27mu-linux_x86_64.whl pip install https://paddle-wheel.bj.bcebos.com/2.0.0-gpu-cuda9-cudnn7-mkl/paddlepaddle_gpu-2.0.0.post90-cp27-cp27mu-linux_x86_64.whl
``` ```
由于默认的`paddlepaddle-gpu==2.0.0`是Cuda 10.2,并没有联编TensorRT,因此如果需要和在`paddlepaddle-gpu`上使用TensorRT,需要在上述多版本whl包列表当中,找到`cuda10.2-cudnn8.0-trt7.1.3`,下载对应的Python版本。 由于默认的`paddlepaddle-gpu==2.0.0`是Cuda 10.2,并没有联编TensorRT,因此如果需要和在`paddlepaddle-gpu`上使用TensorRT,需要在上述多版本whl包列表当中,找到`cuda10.2-cudnn8.0-trt7.1.3`,下载对应的Python版本。更多信息请参考[如何使用TensorRT?](doc/TENSOR_RT_CN.md)
如果是其他环境和Python版本,请在表格中找到对应的链接并用pip安装。 如果是其他环境和Python版本,请在表格中找到对应的链接并用pip安装。
...@@ -222,6 +222,7 @@ curl -H "Content-Type:application/json" -X POST -d '{"feed":[{"x": [0.0137, -0.1 ...@@ -222,6 +222,7 @@ curl -H "Content-Type:application/json" -X POST -d '{"feed":[{"x": [0.0137, -0.1
- [如何开发Pipeline?](doc/PIPELINE_SERVING_CN.md) - [如何开发Pipeline?](doc/PIPELINE_SERVING_CN.md)
- [如何使用uWSGI部署Web Service](doc/UWSGI_DEPLOY_CN.md) - [如何使用uWSGI部署Web Service](doc/UWSGI_DEPLOY_CN.md)
- [如何实现模型文件热加载](doc/HOT_LOADING_IN_SERVING_CN.md) - [如何实现模型文件热加载](doc/HOT_LOADING_IN_SERVING_CN.md)
- [如何使用TensorRT?](doc/TENSOR_RT_CN.md)
### 关于Paddle Serving性能 ### 关于Paddle Serving性能
- [如何测试Paddle Serving性能?](python/examples/util/) - [如何测试Paddle Serving性能?](python/examples/util/)
......
## Paddle Serving uses TensorRT ## Paddle Serving uses TensorRT
(English|[Simplified Chinese]((./TENSOR_RT_CN.md))) (English|[简体中文]((./TENSOR_RT_CN.md)))
### Background ### Background
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册