diff --git a/doc/DOCKER_IMAGES.md b/doc/DOCKER_IMAGES.md index cf5023c18365bd1994f1192d6faae0c77f3c49db..aa60c2cac40b45d27ac257859c2c1e9b3f75ef13 100644 --- a/doc/DOCKER_IMAGES.md +++ b/doc/DOCKER_IMAGES.md @@ -97,3 +97,5 @@ Running Images: | | <=0.4.0 | Nan | Nan | Nan | | Cuda11.0 | 0.5.0 | 0.5.0-cuda11.0-cudnn8 | Ubuntu 18 | 8.2.0 | | | <=0.4.0 | Nan | Nan | Nan | + +**Tips:** If you want to use CPU server and GPU server (version>=0.5.0) at the same time, you should check the gcc version, only Cuda10.1/10.2/11 can run with CPU server owing to the same gcc version(8.2). diff --git a/doc/DOCKER_IMAGES_CN.md b/doc/DOCKER_IMAGES_CN.md index d84b6f8d2834480c7ab8228309fbe1e75a375d63..05f5f87c18377ce5c2473f3525f9d46536ed1a90 100644 --- a/doc/DOCKER_IMAGES_CN.md +++ b/doc/DOCKER_IMAGES_CN.md @@ -102,3 +102,4 @@ registry.baidubce.com/paddlepaddle/serving:xpu-beta | Cuda11.0 | 0.5.0 | 0.5.0-cuda11.0-cudnn8 | Ubuntu 18 | 8.2.0 | | | <=0.4.0 | Nan | Nan | Nan | +**注意事项：** 如果您在0.5.0及以上版本需要在一个容器当中同时运行CPU server和GPU server，需要选择Cuda10.1/10.2/11的镜像，因为他们和CPU环境有着相同版本的gcc。 diff --git a/doc/LATEST_PACKAGES.md b/doc/LATEST_PACKAGES.md index d21a102f661865cd51675ac54277cd89d0397534..d034fafa6e7cc588511beccff11d4beeaa5ba72e 100644 --- a/doc/LATEST_PACKAGES.md +++ b/doc/LATEST_PACKAGES.md @@ -3,41 +3,44 @@ ## CPU server ### Python 3 ``` +# Compile by gcc8.2 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server-0.0.0-py3-none-any.whl ``` ### Python 2 ``` +# Compile by gcc8.2 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server-0.0.0-py2-none-any.whl ``` ## GPU server ### Python 3 ``` -#cuda 9.0 +#cuda 9.0, Compile by gcc4.8 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post9-py3-none-any.whl -#cuda 10.0 +#cuda 10.0, Compile by gcc4.8 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post10-py3-none-any.whl -#cuda10.1 with TensorRT 6 +#cuda10.1 with TensorRT 6, Compile by gcc8.2 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post101-py3-none-any.whl -#cuda10.2 with TensorRT 7 +#cuda10.2 with TensorRT 7, Compile by gcc8.2 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post102-py3-none-any.whl -#cuda11.0 with TensorRT 7 (beta) +#cuda11.0 with TensorRT 7 (beta), Compile by gcc8.2 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post11-py3-none-any.whl ``` ### Python 2 ``` -#cuda 9.0 +#cuda 9.0, Compile by gcc4.8 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post9-py2-none-any.whl -#cuda 10.0 +#cuda 10.0, Compile by gcc4.8 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post10-py2-none-any.whl -#cuda10.1 with TensorRT 6 +#cuda10.1 with TensorRT 6, Compile by gcc8.2 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post101-py2-none-any.whl -#cuda10.2 with TensorRT 7 +#cuda10.2 with TensorRT 7, Compile by gcc8.2 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post102-py2-none-any.whl -#cuda11.0 with TensorRT 7 (beta) +#cuda11.0 with TensorRT 7 (beta), Compile by gcc8.2 https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post11-py2-none-any.whl ``` +**Tips:** If you want to use CPU server and GPU server at the same time, you should check the gcc version, only Cuda10.1/10.2/11 can run with CPU server owing to the same gcc version(8.2). ## Client diff --git a/doc/RUN_IN_DOCKER.md b/doc/RUN_IN_DOCKER.md index debe08a96b9512759473022c094d9115b24805fa..46b18300b01aa117b95b265c95623062711d14c9 100644 --- a/doc/RUN_IN_DOCKER.md +++ b/doc/RUN_IN_DOCKER.md @@ -73,4 +73,5 @@ If you need to change the version, please refer to the instructions on the homep ## Precautious -Runtime images cannot be used for compilation. If you want to compile from source, refer to [COMPILE](COMPILE.md). +- Runtime images cannot be used for compilation. If you want to compile from source, refer to [COMPILE](COMPILE.md). +- If you use Cuda9 and Cuda10 docker images, you cannot use `paddle_serving_server` CPU version at the same time, due to the limitation of gcc version. If you want to use both in one docker image, please choose images of Cuda10.1, Cuda10.2 and Cuda11. diff --git a/doc/RUN_IN_DOCKER_CN.md b/doc/RUN_IN_DOCKER_CN.md index 7dfc3eee62b3bf8f6d925b97e3d7da3fd51ad423..570225f034fbf9834d7acf164debf7f16489f4f6 100644 --- a/doc/RUN_IN_DOCKER_CN.md +++ b/doc/RUN_IN_DOCKER_CN.md @@ -65,4 +65,5 @@ docker exec -it test bash ## 注意事项 -运行时镜像不能用于开发编译。如果想要从源码编译，请查看[如何编译PaddleServing](COMPILE.md)。 +- 运行时镜像不能用于开发编译。如果想要从源码编译，请查看[如何编译PaddleServing](COMPILE.md)。 +- 由于Cuda10和Cuda9的环境受限于GCC版本，无法同时运行CPU版本的`paddle_serving_server`，因此如果想要在GPU环境中同时使用CPU版本的`paddle_serving_server`，请选择Cuda10.1，Cuda10.2和Cuda11版本的镜像。