From 09338b61b0994bacdab450eace8211e9e901d9b8 Mon Sep 17 00:00:00 2001 From: JZZ-NOTE Date: Wed, 28 Sep 2022 07:36:40 +0000 Subject: [PATCH 1/5] Revert "add tensorrt in docs (#5313)" This reverts commit bc1ea59589eb219a2dd58b2a69b71360c30b85ac. --- docs/install/compile/linux-compile.md | 19 +++++---- docs/install/compile/linux-compile_en.md | 13 +++--- docs/install/compile/windows-compile.md | 4 +- docs/install/pip/linux-pip.md | 50 ++++++++++++------------ docs/install/pip/linux-pip_en.md | 49 ++++++++++++----------- docs/install/pip/windows-pip.md | 44 +++++++++++---------- docs/install/pip/windows-pip_en.md | 42 +++++++++++--------- 7 files changed, 116 insertions(+), 105 deletions(-) diff --git a/docs/install/compile/linux-compile.md b/docs/install/compile/linux-compile.md index 0b38415d5be..33c55cef511 100644 --- a/docs/install/compile/linux-compile.md +++ b/docs/install/compile/linux-compile.md @@ -16,15 +16,14 @@ * 如果您的计算机有 NVIDIA® GPU，请确保满足以下条件以编译 GPU 版 PaddlePaddle - * **CUDA 工具包 10.1 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高)** - * **CUDA 工具包 10.2 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.0.0.11)** - * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.2.3.4)** - * **CUDA 工具包 11.2 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.0.3.4)** - * **CUDA 工具包 11.6 配合 cuDNN v8.4.0(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.0.6)** - * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.2.4)** + * **CUDA 工具包 10.1/10.2 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 11.2 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 11.6 配合 cuDNN v8.4.0(如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需多卡支持，需配合 NCCL2.7 及更高)** * **GPU 运算能力超过 3.5 的硬件设备** - 您可参考 NVIDIA 官方文档了解 CUDA 和 CUDNN 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + 您可参考 NVIDIA 官方文档了解 CUDA 和 CUDNN 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) ## 安装步骤 @@ -140,7 +139,7 @@ git checkout [分支名] 例如： ``` -git checkout release/2.3 +git checkout release/2.4 ``` 注意：python3.6、python3.7 版本从 release/1.2 分支开始支持, python3.8 版本从 release/1.8 分支开始支持, python3.9 版本从 release/2.1 分支开始支持, python3.10 版本从 release/2.3 分支开始支持 @@ -489,7 +488,7 @@ git checkout [分支名] 例如： ``` -git checkout release/2.3 +git checkout release/2.4 ``` #### 10. 并且请创建并进入一个叫 build 的目录下： @@ -514,7 +513,7 @@ mkdir build && cd build > 请注意 PY_VERSION 参数更换为您需要的 python 版本 -* 对于需要编译**GPU 版本 PaddlePaddle**的用户：(**仅支持 CentOS7（CUDA11.6/CUDA11.2/CUDA11.1/CUDA10.2/CUDA10.1)**) +* 对于需要编译**GPU 版本 PaddlePaddle**的用户：(**仅支持 CentOS7（CUDA11.7/CUDA11.6/CUDA11.2/CUDA11.1/CUDA10.2/CUDA10.1)**) 1. 请确保您已经正确安装 nccl2，或者按照以下指令安装 nccl2（这里提供的是 CUDA10.2，cuDNN7 下 nccl2 的安装指令，更多版本的安装信息请参考 NVIDIA[官方网站](https://developer.nvidia.com/nccl)）: diff --git a/docs/install/compile/linux-compile_en.md b/docs/install/compile/linux-compile_en.md index 70448cf14a0..57214a36669 100644 --- a/docs/install/compile/linux-compile_en.md +++ b/docs/install/compile/linux-compile_en.md @@ -16,15 +16,14 @@ * If your computer has NVIDIA® GPU, and the following conditions are met，GPU version of PaddlePaddle is recommended. - * **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)** - * **CUDA toolkit 10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.0.0.11)** - * **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.2.3.4)** - * **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.0.3.4)** - * **CUDA toolkit 11.6 with cuDNN v8.4.0(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.4.0.6)** - * **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.4.2.4)** + * **CUDA toolkit 10.1/10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 11.6 with cuDNN v8.4.0(for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher)** * **Hardware devices with GPU computing power over 3.5** - You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + You can refer to NVIDIA official documents for installation process and configuration method of CUDA and cudnn. Please refer to[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) ## Installation steps diff --git a/docs/install/compile/windows-compile.md b/docs/install/compile/windows-compile.md index 38a2da15ba9..d163b01c42b 100644 --- a/docs/install/compile/windows-compile.md +++ b/docs/install/compile/windows-compile.md @@ -15,7 +15,7 @@ * 如果你的计算机硬件没有 NVIDIA® GPU，请编译 CPU 版本的 PaddlePaddle -* 如果你的计算机硬件有 NVIDIA® GPU，推荐编译 GPU 版本的 PaddlePaddle，建议安装 **CUDA 10.1/10.2//11.1/11.2/11.6/11.7** +* 如果你的计算机硬件有 NVIDIA® GPU，推荐编译 GPU 版本的 PaddlePaddle，建议安装 **CUDA 10.1/10.2/11.1/11.2/11.6/11.7** ## 本机编译过程 @@ -51,7 +51,7 @@ 5. 切换到 2.2 分支下进行编译： ``` - git checkout release/2.3 + git checkout release/2.4 ``` 6. 创建名为 build 的目录并进入： diff --git a/docs/install/pip/linux-pip.md b/docs/install/pip/linux-pip.md index d0771f3d201..9cf477ca85f 100644 --- a/docs/install/pip/linux-pip.md +++ b/docs/install/pip/linux-pip.md @@ -6,10 +6,8 @@ * **Linux 版本 (64 bit)** - * **CentOS 7 (GPU 版本支持 CUDA 10.1/10.2/11.1/11.2/11.6)** - * **Ubuntu 16.04 (GPU 版本支持 CUDA 10.1/10.2/11.1/11.2/11.6)** - * **Ubuntu 18.04 (GPU 版本支持 CUDA 10.1/10.2/11.1/11.2/11.6)** - * **Ubuntu 20.04 (GPU 版本支持 CUDA 10.1/10.2/11.1/11.2/11.6)** + * **CentOS 7 (GPU 版本支持 CUDA 10.1/10.2/11.1/11.2/11.6/11.7)** + * **Ubuntu 16.04/18.04/20.04/22.04 (GPU 版本支持 CUDA 10.1/10.2/11.1/11.2/11.6/11.7)** * **Python 版本 3.6/3.7/3.8/3.9/3.10 (64 bit)** @@ -77,21 +75,19 @@ * 如果您的计算机有 NVIDIA® GPU，请确保满足以下条件并且安装[GPU 版 PaddlePaddle](#gpu) - * **CUDA 工具包 10.1 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 10.1/10.2 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高)** - * **CUDA 工具包 10.2 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.0.0.11)** + * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高)** - * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.2.3.4)** + * **CUDA 工具包 11.2 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高)** - * **CUDA 工具包 11.2 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.0.3.4)** + * **CUDA 工具包 11.6 配合 cuDNN v8.4.0(如需多卡支持，需配合 NCCL2.7 及更高)** - * **CUDA 工具包 11.6 配合 cuDNN v8.4.0(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.0.6)** - - * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.2.4)** + * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需多卡支持，需配合 NCCL2.7 及更高)** * **GPU 运算能力超过 3.5 的硬件设备** - 您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + 您可参考 NVIDIA 官方文档了解 CUDA 和 CUDNN 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) * 如果您需要使用多卡环境请确保您已经正确安装 nccl2，或者按照以下指令安装 nccl2（这里提供的是 CUDA10.2，cuDNN7 下 nccl2 的安装指令，更多版本的安装信息请参考 NVIDIA[官方网站](https://developer.nvidia.com/nccl)）: @@ -130,7 +126,7 @@ ``` - python -m pip install paddlepaddle==2.3.2 -i https://pypi.tuna.tsinghua.edu.cn/simple + python -m pip install paddlepaddle==2.4.0rc0 -i https://pypi.tuna.tsinghua.edu.cn/simple ``` @@ -142,7 +138,7 @@ 2.2.1 CUDA10.1 的 PaddlePaddle ``` - python -m pip install paddlepaddle-gpu==2.3.2.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html ``` @@ -151,7 +147,7 @@ ``` - python -m pip install paddlepaddle-gpu==2.3.2 -i https://pypi.tuna.tsinghua.edu.cn/simple + python -m pip install paddlepaddle-gpu==2.4.0rc0 -i https://pypi.tuna.tsinghua.edu.cn/simple ``` @@ -159,7 +155,7 @@ ``` - python -m pip install paddlepaddle-gpu==2.3.2.post111 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post111 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html ``` @@ -167,7 +163,7 @@ ``` - python -m pip install paddlepaddle-gpu==2.3.2.post112 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post112 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html ``` @@ -175,9 +171,15 @@ ``` - python -m pip install paddlepaddle-gpu==2.3.2.post116 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post116 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html ``` +2.2.6 CUDA11.7 的 PaddlePaddle + + + ``` + python -m pip install paddlepaddle-gpu==2.4.0rc0.post117 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html + ``` 注： @@ -199,26 +201,26 @@ * cpu、mkl 版本 noavx 机器安装： ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps ``` * cpu、openblas 版本 noavx 机器安装： ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/linux/openblas/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/linux/openblas/noavx/stable.html --no-index --no-deps ``` * gpu 版本 cuda10.1 noavx 机器安装： ``` - python -m pip download paddlepaddle-gpu==2.3.2.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle-gpu==2.4.0rc0.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps ``` * gpu 版本 cuda10.2 noavx 机器安装： ``` - python -m pip download paddlepaddle-gpu==2.3.2 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle-gpu==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps ``` 判断你的机器是否支持`avx`，可以输入以下命令，如果输出中包含`avx`，则表示机器支持`avx` @@ -229,10 +231,10 @@ * 如果你想安装`avx`、`openblas`的 Paddle 包，可以通过以下命令将 wheel 包下载到本地，再使用`python -m pip install [name].whl`本地安装（[name]为 wheel 包名称）： ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/linux/openblas/avx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/linux/openblas/avx/stable.html --no-index --no-deps ``` -* 如果你想在`cuda11.2`环境下，获得更好的`PaddleTensorRT`推理性能，需配合`cudnn8.2.1`，并安装联编`tensorrt8.0.3.4`的 Paddle 包，可以参考[下载安装 Linux 预测库](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html)。 +* 如果你想安装联编`tensorrt`的 Paddle 包，可以参考[下载安装 Linux 预测库](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html)。 diff --git a/docs/install/pip/linux-pip_en.md b/docs/install/pip/linux-pip_en.md index 2932aaa6119..62b29549c0c 100644 --- a/docs/install/pip/linux-pip_en.md +++ b/docs/install/pip/linux-pip_en.md @@ -6,9 +6,7 @@ * **Linux Version (64 bit)** * **CentOS 7 (GPUVersion Supports CUDA 10.1/10.2/11.1/11.2/11.6/11.7)** - * **Ubuntu 16.04 (GPUVersion Supports CUDA 10.1/10.2/11.1/11.2/11.6/11.7)** - * **Ubuntu 18.04 (GPUVersion Supports CUDA 10.1/10.2/11.1/11.2/11.6/11.7)** - * **Ubuntu 20.04 (GPUVersion Supports CUDA 10.1/10.2/11.1/11.2/11.6/11.7)** + * **Ubuntu 16.04/18.04/20.04/22.04 (GPUVersion Supports CUDA 10.1/10.2/11.1/11.2/11.6/11.7)** * **Python Version: 3.6/3.7/3.8/3.9/3.10 (64 bit)** @@ -77,21 +75,19 @@ If you installed Python via Homebrew or the Python website, `pip` was installed * If your computer has NVIDIA® GPU, please make sure that the following conditions are met and install [the GPU Version of PaddlePaddle](#gpu) - * **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 10.1/10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)** - * **CUDA toolkit 10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.0.0.11)** + * **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher)** - * **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.2.3.4)** + * **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher)** - * **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.0.3.4)** + * **CUDA toolkit 11.6 with cuDNN v8.4.0(for multi card support, NCCL2.7 or higher)** - * **CUDA toolkit 11.6 with cuDNN v8.4.0(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.4.0.6)** - - * **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.4.2.4)** + * **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher)** * **Hardware devices with GPU computing power over 3.5** - You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + You can refer to NVIDIA official documents for installation process and configuration method of CUDA and cudnn. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) * If you need to use a multi-card environment, please make sure that you have installed nccl2 correctly, or install nccl2 according to the following instructions (here are the installation instructions of nccl2 under CUDA10.2 and cuDNN7. For more version installation information, please refer to NVIDIA [Official Website](https://developer.nvidia.com/nccl)): @@ -137,7 +133,7 @@ You can choose the following version of PaddlePaddle to start installation: ``` - python -m pip install paddlepaddle==2.3.2 -i https://pypi.tuna.tsinghua.edu.cn/simple + python -m pip install paddlepaddle==2.4.0rc0 -i https://pypi.tuna.tsinghua.edu.cn/simple ``` @@ -150,7 +146,7 @@ You can choose the following version of PaddlePaddle to start installation: ``` - python -m pip install paddlepaddle-gpu==2.3.2.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html ``` @@ -159,14 +155,14 @@ You can choose the following version of PaddlePaddle to start installation: ``` - python -m pip install paddlepaddle-gpu==2.3.2 -i https://pypi.tuna.tsinghua.edu.cn/simple + python -m pip install paddlepaddle-gpu==2.4.0rc0 -i https://pypi.tuna.tsinghua.edu.cn/simple ``` 2.2.3 If you are using CUDA 11.1 ``` - python -m pip install paddlepaddle-gpu==2.3.2.post111 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post111 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html ``` @@ -174,7 +170,7 @@ You can choose the following version of PaddlePaddle to start installation: ``` - python -m pip install paddlepaddle-gpu==2.3.2.post112 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post112 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html ``` @@ -182,7 +178,14 @@ You can choose the following version of PaddlePaddle to start installation: ``` - python -m pip install paddlepaddle-gpu==2.3.2.post116 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post116 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html + ``` + +2.2.6 If you are using CUDA 11.7 + + + ``` + python -m pip install paddlepaddle-gpu==2.4.0rc0.post117 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html ``` Note： @@ -204,26 +207,26 @@ Note： * cpu and mkl version installed on noavx machine： ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps ``` * cpu and openblas version installed on noavx machine： ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/linux/openblas/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/linux/openblas/noavx/stable.html --no-index --no-deps ``` * GPU cuda10.1 version install on noavx machine： ``` - python -m pip download paddlepaddle-gpu==2.3.2.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle-gpu==2.4.0rc0.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps ``` * GPU cuda10.2 version install on noavx machine： ``` - python -m pip download paddlepaddle-gpu==2.3.2 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle-gpu==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/noavx/stable.html --no-index --no-deps ``` To determine whether your machine supports `avx`, you can use the following command. If the output contains `avx`, it means that the machine supports `avx`: @@ -234,10 +237,10 @@ Note： * If you want to install the Paddle package with `avx` and `openblas`, you can use the following command to download the wheel package to the local, and then use `python -m pip install [name].whl` to install locally ([name] is the name of the wheel package): ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/linux/openblas/avx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/linux/openblas/avx/stable.html --no-index --no-deps ``` -* If you want to get better deployment performance by using PaddleTensorRT for CUDA11.2, you can [download the Paddle package compiled with cuDNN8.2.1 and TensorRT8.0.3.4.](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html) + ## Verify installation diff --git a/docs/install/pip/windows-pip.md b/docs/install/pip/windows-pip.md index ae7fd2933e5..d0186acfc4f 100644 --- a/docs/install/pip/windows-pip.md +++ b/docs/install/pip/windows-pip.md @@ -51,21 +51,19 @@ * 如果您的计算机有 NVIDIA® GPU，请确保满足以下条件并且安装 GPU 版 PaddlePaddle - * **CUDA 工具包 10.1 配合 cuDNN v7.6.5** + * **CUDA 工具包 10.1/10.2 配合 cuDNN v7.6.5** - * **CUDA 工具包 10.2 配合 cuDNN v7.6.5(如需使用 PaddleTensorRT 推理，需配合 TensorRT7.0.0.11)** + * **CUDA 工具包 11.1 配合 cuDNN v8.1.1** - * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需使用 PaddleTensorRT 推理，需配合 TensorRT8.0.3.4)** + * **CUDA 工具包 11.2 配合 cuDNN v8.2.1** - * **CUDA 工具包 11.2 配合 cuDNN v8.2.1(如需使用 PaddleTensorRT 推理，需配合 TensorRT8.2.4.2)** + * **CUDA 工具包 11.6 配合 cuDNN v8.4.0** - * **CUDA 工具包 11.6 配合 cuDNN v8.4.0(如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.0.6)** - - * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.2.4)** + * **CUDA 工具包 11.7 配合 cuDNN v8.4.1** * **GPU 运算能力超过 3.5 的硬件设备** - * 注：目前官方发布的 windows 安装包仅包含 CUDA 10.1/10.2/11.1/11.2/11.6/11.7，如需使用其他 cuda 版本，请通过源码自行编译。您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + * 注：目前官方发布的 windows 安装包仅包含 CUDA 10.1/10.2/11.1/11.2/11.6/11.7，如需使用其他 cuda 版本，请通过源码自行编译。您可参考 NVIDIA 官方文档了解 CUDA 和 CUDNN 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) @@ -78,7 +76,7 @@ ``` - python -m pip install paddlepaddle==2.3.2 -i https://pypi.tuna.tsinghua.edu.cn/simple + python -m pip install paddlepaddle==2.4.0rc0 -i https://pypi.tuna.tsinghua.edu.cn/simple ``` #### 2.2 GPU 版的 PaddlePaddle @@ -89,7 +87,7 @@ ``` - python -m pip install paddlepaddle-gpu==2.3.2.post101 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post101 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html ``` @@ -97,28 +95,34 @@ ``` - python -m pip install paddlepaddle-gpu==2.3.2 -i https://pypi.tuna.tsinghua.edu.cn/simple + python -m pip install paddlepaddle-gpu==2.4.0rc0 -i https://pypi.tuna.tsinghua.edu.cn/simple ``` 2.2.3 CUDA11.1 的 PaddlePaddle ``` - python -m pip install paddlepaddle-gpu==2.3.2.post111 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post111 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html ``` 2.2.4 CUDA11.2 的 PaddlePaddle ``` - python -m pip install paddlepaddle-gpu==2.3.2.post112 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post112 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html ``` 2.2.5 CUDA11.6 的 PaddlePaddle ``` - python -m pip install paddlepaddle-gpu==2.3.2.post116 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post116 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html + ``` + +2.2.6 CUDA11.7 的 PaddlePaddle + + ``` + python -m pip install paddlepaddle-gpu==2.4.0rc0.post117 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html ``` @@ -135,25 +139,25 @@ * cpu、mkl 版本 noavx 机器安装： ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps ``` * cpu、openblas 版本 noavx 机器安装： ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/windows/openblas/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/windows/openblas/noavx/stable.html --no-index --no-deps ``` * gpu 版本 cuda10.1 noavx 机器安装： ``` - python -m pip download paddlepaddle-gpu==2.3.2.post101 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle-gpu==2.4.0rc0.post101 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps ``` * gpu 版本 cuda10.2 noavx 机器安装： ``` - python -m pip download paddlepaddle-gpu==2.3.2 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle-gpu==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps ``` 判断你的机器是否支持`avx`，可以安装[CPU-Z](https://www.cpuid.com/softwares/cpu-z.html)工具查看“处理器-指令集”。 @@ -161,10 +165,10 @@ * 如果你想安装`avx`、`openblas`的 Paddle 包，可以通过以下命令将 wheel 包下载到本地，再使用`python -m pip install [name].whl`本地安装（[name]为 wheel 包名称）： ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/windows/openblas/avx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/windows/openblas/avx/stable.html --no-index --no-deps ``` - +* 如果你想安装联编`tensorrt`的 Paddle 包，可以参考[下载安装 Windows 预测库](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#windows)。 diff --git a/docs/install/pip/windows-pip_en.md b/docs/install/pip/windows-pip_en.md index b830696b417..533c765e702 100644 --- a/docs/install/pip/windows-pip_en.md +++ b/docs/install/pip/windows-pip_en.md @@ -50,21 +50,19 @@ If you installed Python via Homebrew or the Python website, `pip` was installed * If your computer has NVIDIA® GPU, please make sure that the following conditions are met and install [the GPU Version of PaddlePaddle](#gpu) - * **CUDA toolkit 10.1 with cuDNN v7.6.5** + * **CUDA toolkit 10.1/10.2 with cuDNN v7.6.5** - * **CUDA toolkit 10.2 with cuDNN v7.6.5(for PaddleTensorRT deployment, TensorRT7.0.0.11)** + * **CUDA toolkit 11.1 with cuDNN v8.1.1** - * **CUDA toolkit 11.1 with cuDNN v8.1.1(for PaddleTensorRT deployment, TensorRT8.0.3.4)** + * **CUDA toolkit 11.2 with cuDNN v8.2.1** - * **CUDA toolkit 11.2 with cuDNN v8.2.1(for PaddleTensorRT deployment, TensorRT8.2.4.2)** + * **CUDA toolkit 11.6 with cuDNN v8.4.0** - * **CUDA toolkit 11.6 with cuDNN v8.4.0(for PaddleTensorRT deployment, TensorRT8.4.0.6)** - - * **CUDA toolkit 11.7 with cuDNN v8.4.1(for PaddleTensorRT deployment, TensorRT8.4.2.4)** + * **CUDA toolkit 11.7 with cuDNN v8.4.1** * **GPU CUDA capability over 3.5** - You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + You can refer to NVIDIA official documents for installation process and configuration method of CUDA and cudnn. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) ## Installation Step @@ -77,7 +75,7 @@ You can choose the following version of PaddlePaddle to start installation: ``` - python -m pip install paddlepaddle==2.3.2 -i https://pypi.tuna.tsinghua.edu.cn/simple + python -m pip install paddlepaddle==2.4.0rc0 -i https://pypi.tuna.tsinghua.edu.cn/simple ``` @@ -89,34 +87,40 @@ You can choose the following version of PaddlePaddle to start installation: ``` - python -m pip install paddlepaddle-gpu==2.3.2.post101 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post101 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html ``` 2.2.2 If you are using CUDA 10.2 ``` - python -m pip install paddlepaddle-gpu==2.3.2 -i https://pypi.tuna.tsinghua.edu.cn/simple + python -m pip install paddlepaddle-gpu==2.4.0rc0 -i https://pypi.tuna.tsinghua.edu.cn/simple ``` 2.2.3 If you are using CUDA 11.1 ``` - python -m pip install paddlepaddle-gpu==2.3.2.post111 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post111 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html ``` 2.2.4 If you are using CUDA 11.2 ``` - python -m pip install paddlepaddle-gpu==2.3.2.post112 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post112 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html ``` 2.2.5 If you are using CUDA 11.6 ``` - python -m pip install paddlepaddle-gpu==2.3.2.post116 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html + python -m pip install paddlepaddle-gpu==2.4.0rc0.post116 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html + ``` + +2.2.6 If you are using CUDA 11.7 + + ``` + python -m pip install paddlepaddle-gpu==2.4.0rc0.post117 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/avx/stable.html ``` Note： @@ -132,25 +136,25 @@ Note： * cpu and mkl version installed on noavx machine： ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps ``` * cpu and openblas version installed on noavx machine： ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/windows/openblas/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/windows/openblas/noavx/stable.html --no-index --no-deps ``` * GPU cuda10.1 version install on noavx machine： ``` - python -m pip download paddlepaddle-gpu==2.3.2.post101 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle-gpu==2.4.0rc0.post101 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps ``` * GPU cuda10.2 version install on noavx machine： ``` - python -m pip download paddlepaddle-gpu==2.3.2 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps + python -m pip download paddlepaddle-gpu==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/windows/mkl/noavx/stable.html --no-index --no-deps ``` To determine whether your machine supports `avx`, you can install the [CPU-Z](https://www.cpuid.com/softwares/cpu-z.html) tool to view the "processor-instruction set". @@ -159,7 +163,7 @@ Note： * If you want to install the Paddle package with `avx` and `openblas`, you can use the following command to download the wheel package to the local, and then use `python -m pip install [name].whl` to install locally ([name] is the name of the wheel package): ``` - python -m pip download paddlepaddle==2.3.2 -f https://www.paddlepaddle.org.cn/whl/windows/openblas/avx/stable.html --no-index --no-deps + python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/windows/openblas/avx/stable.html --no-index --no-deps ``` ## Verify installation From dac958651b6e2e99ecd94c139be54da5f6971875 Mon Sep 17 00:00:00 2001 From: JZZ-NOTE Date: Wed, 28 Sep 2022 07:45:22 +0000 Subject: [PATCH 2/5] add tensorrt install --- docs/install/compile/linux-compile.md | 13 +++++++------ docs/install/compile/linux-compile_en.md | 2 +- docs/install/pip/linux-pip.md | 16 +++++++++------- docs/install/pip/linux-pip_en.md | 14 ++++++++------ docs/install/pip/windows-pip.md | 15 ++++++++------- docs/install/pip/windows-pip_en.md | 14 ++++++++------ 6 files changed, 41 insertions(+), 33 deletions(-) diff --git a/docs/install/compile/linux-compile.md b/docs/install/compile/linux-compile.md index 33c55cef511..4201c19e8f6 100644 --- a/docs/install/compile/linux-compile.md +++ b/docs/install/compile/linux-compile.md @@ -16,14 +16,15 @@ * 如果您的计算机有 NVIDIA® GPU，请确保满足以下条件以编译 GPU 版 PaddlePaddle - * **CUDA 工具包 10.1/10.2 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高)** - * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高)** - * **CUDA 工具包 11.2 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高)** - * **CUDA 工具包 11.6 配合 cuDNN v8.4.0(如需多卡支持，需配合 NCCL2.7 及更高)** - * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 10.1 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 10.2 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.0.0.11)** + * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.2.3.4)** + * **CUDA 工具包 11.2 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.0.3.4)** + * **CUDA 工具包 11.6 配合 cuDNN v8.4.0(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.0.6)** + * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.2.4)** * **GPU 运算能力超过 3.5 的硬件设备** - 您可参考 NVIDIA 官方文档了解 CUDA 和 CUDNN 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) + 您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) ## 安装步骤 diff --git a/docs/install/compile/linux-compile_en.md b/docs/install/compile/linux-compile_en.md index 57214a36669..b2d31a6d13d 100644 --- a/docs/install/compile/linux-compile_en.md +++ b/docs/install/compile/linux-compile_en.md @@ -23,7 +23,7 @@ * **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher)** * **Hardware devices with GPU computing power over 3.5** - You can refer to NVIDIA official documents for installation process and configuration method of CUDA and cudnn. Please refer to[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) + You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) ## Installation steps diff --git a/docs/install/pip/linux-pip.md b/docs/install/pip/linux-pip.md index 9cf477ca85f..e49a51ee75c 100644 --- a/docs/install/pip/linux-pip.md +++ b/docs/install/pip/linux-pip.md @@ -75,19 +75,21 @@ * 如果您的计算机有 NVIDIA® GPU，请确保满足以下条件并且安装[GPU 版 PaddlePaddle](#gpu) - * **CUDA 工具包 10.1/10.2 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 10.1 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高)** - * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 10.2 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.0.0.11)** - * **CUDA 工具包 11.2 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.2.3.4)** - * **CUDA 工具包 11.6 配合 cuDNN v8.4.0(如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 11.2 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.0.3.4)** - * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 11.6 配合 cuDNN v8.4.0(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.0.6)** + + * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.2.4)** * **GPU 运算能力超过 3.5 的硬件设备** - 您可参考 NVIDIA 官方文档了解 CUDA 和 CUDNN 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) + 您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) * 如果您需要使用多卡环境请确保您已经正确安装 nccl2，或者按照以下指令安装 nccl2（这里提供的是 CUDA10.2，cuDNN7 下 nccl2 的安装指令，更多版本的安装信息请参考 NVIDIA[官方网站](https://developer.nvidia.com/nccl)）: @@ -234,7 +236,7 @@ python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/linux/openblas/avx/stable.html --no-index --no-deps ``` -* 如果你想安装联编`tensorrt`的 Paddle 包，可以参考[下载安装 Linux 预测库](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html)。 +* 如果你想在`cuda11.2`环境下，获得更好的`PaddleTensorRT`推理性能，需配合`cudnn8.2.1`，并安装联编`tensorrt8.0.3.4`的 Paddle 包，可以参考[下载安装 Linux 预测库](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html)。 diff --git a/docs/install/pip/linux-pip_en.md b/docs/install/pip/linux-pip_en.md index 62b29549c0c..9da0d3e6104 100644 --- a/docs/install/pip/linux-pip_en.md +++ b/docs/install/pip/linux-pip_en.md @@ -75,19 +75,21 @@ If you installed Python via Homebrew or the Python website, `pip` was installed * If your computer has NVIDIA® GPU, please make sure that the following conditions are met and install [the GPU Version of PaddlePaddle](#gpu) - * **CUDA toolkit 10.1/10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)** - * **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.0.0.11)** - * **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.2.3.4)** - * **CUDA toolkit 11.6 with cuDNN v8.4.0(for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.0.3.4)** - * **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 11.6 with cuDNN v8.4.0(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.4.0.6)** + + * **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.4.2.4)** * **Hardware devices with GPU computing power over 3.5** - You can refer to NVIDIA official documents for installation process and configuration method of CUDA and cudnn. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) + You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) * If you need to use a multi-card environment, please make sure that you have installed nccl2 correctly, or install nccl2 according to the following instructions (here are the installation instructions of nccl2 under CUDA10.2 and cuDNN7. For more version installation information, please refer to NVIDIA [Official Website](https://developer.nvidia.com/nccl)): diff --git a/docs/install/pip/windows-pip.md b/docs/install/pip/windows-pip.md index d0186acfc4f..f25e72905cd 100644 --- a/docs/install/pip/windows-pip.md +++ b/docs/install/pip/windows-pip.md @@ -51,19 +51,21 @@ * 如果您的计算机有 NVIDIA® GPU，请确保满足以下条件并且安装 GPU 版 PaddlePaddle - * **CUDA 工具包 10.1/10.2 配合 cuDNN v7.6.5** + * **CUDA 工具包 10.1 配合 cuDNN v7.6.5** - * **CUDA 工具包 11.1 配合 cuDNN v8.1.1** + * **CUDA 工具包 10.2 配合 cuDNN v7.6.5(如需使用 PaddleTensorRT 推理，需配合 TensorRT7.0.0.11)** - * **CUDA 工具包 11.2 配合 cuDNN v8.2.1** + * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需使用 PaddleTensorRT 推理，需配合 TensorRT8.0.3.4)** - * **CUDA 工具包 11.6 配合 cuDNN v8.4.0** + * **CUDA 工具包 11.2 配合 cuDNN v8.2.1(如需使用 PaddleTensorRT 推理，需配合 TensorRT8.2.4.2)** - * **CUDA 工具包 11.7 配合 cuDNN v8.4.1** + * **CUDA 工具包 11.6 配合 cuDNN v8.4.0(如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.0.6)** + + * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.2.4)** * **GPU 运算能力超过 3.5 的硬件设备** - * 注：目前官方发布的 windows 安装包仅包含 CUDA 10.1/10.2/11.1/11.2/11.6/11.7，如需使用其他 cuda 版本，请通过源码自行编译。您可参考 NVIDIA 官方文档了解 CUDA 和 CUDNN 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) + * 注：目前官方发布的 windows 安装包仅包含 CUDA 10.1/10.2/11.1/11.2/11.6/11.7，如需使用其他 cuda 版本，请通过源码自行编译。您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) @@ -168,7 +170,6 @@ python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/windows/openblas/avx/stable.html --no-index --no-deps ``` -* 如果你想安装联编`tensorrt`的 Paddle 包，可以参考[下载安装 Windows 预测库](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#windows)。 diff --git a/docs/install/pip/windows-pip_en.md b/docs/install/pip/windows-pip_en.md index 533c765e702..dd0b0e5cd55 100644 --- a/docs/install/pip/windows-pip_en.md +++ b/docs/install/pip/windows-pip_en.md @@ -50,19 +50,21 @@ If you installed Python via Homebrew or the Python website, `pip` was installed * If your computer has NVIDIA® GPU, please make sure that the following conditions are met and install [the GPU Version of PaddlePaddle](#gpu) - * **CUDA toolkit 10.1/10.2 with cuDNN v7.6.5** + * **CUDA toolkit 10.1 with cuDNN v7.6.5** - * **CUDA toolkit 11.1 with cuDNN v8.1.1** + * **CUDA toolkit 10.2 with cuDNN v7.6.5(for PaddleTensorRT deployment, TensorRT7.0.0.11)** - * **CUDA toolkit 11.2 with cuDNN v8.2.1** + * **CUDA toolkit 11.1 with cuDNN v8.1.1(for PaddleTensorRT deployment, TensorRT8.0.3.4)** - * **CUDA toolkit 11.6 with cuDNN v8.4.0** + * **CUDA toolkit 11.2 with cuDNN v8.2.1(for PaddleTensorRT deployment, TensorRT8.2.4.2)** - * **CUDA toolkit 11.7 with cuDNN v8.4.1** + * **CUDA toolkit 11.6 with cuDNN v8.4.0(for PaddleTensorRT deployment, TensorRT8.4.0.6)** + + * **CUDA toolkit 11.7 with cuDNN v8.4.1(for PaddleTensorRT deployment, TensorRT8.4.2.4)** * **GPU CUDA capability over 3.5** - You can refer to NVIDIA official documents for installation process and configuration method of CUDA and cudnn. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/) + You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) ## Installation Step From 4d4a98affc05d0b37548e908f67063a53e5fa1dd Mon Sep 17 00:00:00 2001 From: JZZ-NOTE Date: Wed, 28 Sep 2022 07:50:36 +0000 Subject: [PATCH 3/5] add tensorrt install --- docs/install/compile/linux-compile_en.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/docs/install/compile/linux-compile_en.md b/docs/install/compile/linux-compile_en.md index b2d31a6d13d..2c7f77d69d8 100644 --- a/docs/install/compile/linux-compile_en.md +++ b/docs/install/compile/linux-compile_en.md @@ -16,11 +16,12 @@ * If your computer has NVIDIA® GPU, and the following conditions are met，GPU version of PaddlePaddle is recommended. - * **CUDA toolkit 10.1/10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)** - * **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher)** - * **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher)** - * **CUDA toolkit 11.6 with cuDNN v8.4.0(for multi card support, NCCL2.7 or higher)** - * **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.0.0.11)** + * **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.2.3.4)** + * **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.0.3.4)** + * **CUDA toolkit 11.6 with cuDNN v8.4.0(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.4.0.6)** + * **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.4.2.4)** * **Hardware devices with GPU computing power over 3.5** You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) From 28236384d6cde060ba54b9a56f4fed0bff5eb205 Mon Sep 17 00:00:00 2001 From: JZZ-NOTE Date: Wed, 28 Sep 2022 10:57:46 +0000 Subject: [PATCH 4/5] modify details --- .../paddle_tensorrt_infer.md | 2 +- .../paddle_tensorrt_infer_en.md | 2 +- docs/install/compile/linux-compile.md | 4 ++-- docs/install/compile/linux-compile_en.md | 4 ++-- docs/install/conda/linux-conda.md | 2 +- docs/install/conda/windows-conda.md | 4 +--- docs/install/pip/linux-pip.md | 15 ++++++++++----- docs/install/pip/linux-pip_en.md | 4 ++-- docs/install/pip/macos-pip.md | 2 ++ docs/install/pip/windows-pip.md | 6 ++++-- docs/install/pip/windows-pip_en.md | 4 ++-- 11 files changed, 28 insertions(+), 21 deletions(-) diff --git a/docs/guides/performance_improving/paddle_tensorrt_infer.md b/docs/guides/performance_improving/paddle_tensorrt_infer.md index 2890eceb4ab..4590884c5a8 100644 --- a/docs/guides/performance_improving/paddle_tensorrt_infer.md +++ b/docs/guides/performance_improving/paddle_tensorrt_infer.md @@ -60,7 +60,7 @@ config->EnableTensorRtEngine(1 << 20 /* workspace_size*/, ## Paddle-TRT 样例编译测试 1. 下载或编译带有 TensorRT 的 paddle 预测库，参考[安装与编译 C++预测库](../../inference_deployment/inference/build_and_install_lib_cn.html)。 -2. 从[NVIDIA 官网](https://developer.nvidia.com/nvidia-tensorrt-download)下载对应本地环境中 cuda 和 cudnn 版本的 TensorRT，需要登陆 NVIDIA 开发者账号。 +2. 从[NVIDIA 官网](https://developer.nvidia.com/tensorrt)下载对应本地环境中 cuda 和 cudnn 版本的 TensorRT，需要登陆 NVIDIA 开发者账号。 3. 下载[预测样例](https://paddle-inference-dist.bj.bcebos.com/tensorrt_test/paddle_inference_sample_v1.7.tar.gz)并解压，进入`sample/paddle-TRT`目录下。 `paddle-TRT` 文件夹目录结构如下： diff --git a/docs/guides/performance_improving/paddle_tensorrt_infer_en.md b/docs/guides/performance_improving/paddle_tensorrt_infer_en.md index 0acc384ab2a..29bd16445b9 100644 --- a/docs/guides/performance_improving/paddle_tensorrt_infer_en.md +++ b/docs/guides/performance_improving/paddle_tensorrt_infer_en.md @@ -53,7 +53,7 @@ The details of this interface is as following: ## Paddle-TRT example compiling test 1. Download or compile Paddle Inference with TensorRT support, refer to [Install and Compile C++ Inference Library](../../inference_deployment/inference/build_and_install_lib_en.html). -2. Download NVIDIA TensorRT(with consistent version of cuda and cudnn in local environment) from [NVIDIA TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) with an NVIDIA developer account. +2. Download NVIDIA TensorRT(with consistent version of cuda and cudnn in local environment) from [NVIDIA TensorRT](https://developer.nvidia.com/tensorrt) with an NVIDIA developer account. 3. Download [Paddle Inference sample](https://paddle-inference-dist.bj.bcebos.com/tensorrt_test/paddle_inference_sample_v1.7.tar.gz) and uncompress, and enter `sample/paddle-TRT` directory. `paddle-TRT` directory structure is as following: diff --git a/docs/install/compile/linux-compile.md b/docs/install/compile/linux-compile.md index 4201c19e8f6..12ed39b9fe9 100644 --- a/docs/install/compile/linux-compile.md +++ b/docs/install/compile/linux-compile.md @@ -16,7 +16,7 @@ * 如果您的计算机有 NVIDIA® GPU，请确保满足以下条件以编译 GPU 版 PaddlePaddle - * **CUDA 工具包 10.1 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 10.1 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高；不支持使用 TensorRT)** * **CUDA 工具包 10.2 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.0.0.11)** * **CUDA 工具包 11.1 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.2.3.4)** * **CUDA 工具包 11.2 配合 cuDNN v8.1.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.0.3.4)** @@ -24,7 +24,7 @@ * **CUDA 工具包 11.7 配合 cuDNN v8.4.1(如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT8.4.2.4)** * **GPU 运算能力超过 3.5 的硬件设备** - 您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + 您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/tensorrt) ## 安装步骤 diff --git a/docs/install/compile/linux-compile_en.md b/docs/install/compile/linux-compile_en.md index 2c7f77d69d8..4770bf1717f 100644 --- a/docs/install/compile/linux-compile_en.md +++ b/docs/install/compile/linux-compile_en.md @@ -16,7 +16,7 @@ * If your computer has NVIDIA® GPU, and the following conditions are met，GPU version of PaddlePaddle is recommended. - * **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher；TensorRT is not support)** * **CUDA toolkit 10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.0.0.11)** * **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.2.3.4)** * **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.0.3.4)** @@ -24,7 +24,7 @@ * **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.4.2.4)** * **Hardware devices with GPU computing power over 3.5** - You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/tensorrt) ## Installation steps diff --git a/docs/install/conda/linux-conda.md b/docs/install/conda/linux-conda.md index e6662874f2f..d4a64bb2ef8 100644 --- a/docs/install/conda/linux-conda.md +++ b/docs/install/conda/linux-conda.md @@ -1,6 +1,6 @@ # Linux 下的 Conda 安装 -[Anaconda](https://www.anaconda.com/)是一个免费开源的 Python 和 R 语言的发行版本，用于计算科学，Anaconda 致力于简化包管理和部署。Anaconda 的包使用软件包管理系统 Conda 进行管理。Conda 是一个开源包管理系统和环境管理系统，可在 Windows、macOS 和 Linux 上运行。 +[Anaconda](https://www.anaconda.com/)是一个免费开源的 Python 和 R 语言的发行版本，用于计算科学，Anaconda 致力于简化包管理和部署。Anaconda 的包使用软件包管理系统 Conda 进行管理。Conda 是一个开源包管理系统和环境管理系统，可在 Windows、macOS 和 Linux 上运行。本文档为你介绍 Anaconda 安装方式，飞桨提供的 Anaconda 安装包支持分布式训练（多机多卡）、TensorRT 推理功能。 ## 一、环境准备 diff --git a/docs/install/conda/windows-conda.md b/docs/install/conda/windows-conda.md index 9ecd6a3343d..e08fda606df 100644 --- a/docs/install/conda/windows-conda.md +++ b/docs/install/conda/windows-conda.md @@ -1,8 +1,6 @@ # Windows 下的 Conda 安装 -[Anaconda](https://www.anaconda.com/)是一个免费开源的 Python 和 R 语言的发行版本，用于计算科学，Anaconda 致力于简化包管理和部署。Anaconda 的包使用软件包管理系统 Conda 进行管理。Conda 是一个开源包管理系统和环境管理系统，可在 Windows、macOS 和 Linux 上运行。 - - +[Anaconda](https://www.anaconda.com/)是一个免费开源的 Python 和 R 语言的发行版本，用于计算科学，Anaconda 致力于简化包管理和部署。Anaconda 的包使用软件包管理系统 Conda 进行管理。Conda 是一个开源包管理系统和环境管理系统，可在 Windows、macOS 和 Linux 上运行。本文档为你介绍 Anaconda 安装方式，飞桨提供的 Anaconda 安装包支持分布式训练（多机多卡）、TensorRT 推理功能。 ## 一、环境准备 diff --git a/docs/install/pip/linux-pip.md b/docs/install/pip/linux-pip.md index e49a51ee75c..d791993c77f 100644 --- a/docs/install/pip/linux-pip.md +++ b/docs/install/pip/linux-pip.md @@ -1,5 +1,7 @@ # Linux 下的 PIP 安装 +The Python Package Index(PyPI)是 Python 的包管理器。本文档为你介绍 PyPI 安装方式，飞桨提供的 PyPI 安装包支持分布式训练（多机多卡）、TensorRT 推理功能；PyPI 下载详见 PyPI 官网（PyPI 官网设置链接：https://pypi.org/）。 + ## 一、环境准备 ### 1.1 目前飞桨支持的环境 @@ -75,7 +77,7 @@ * 如果您的计算机有 NVIDIA® GPU，请确保满足以下条件并且安装[GPU 版 PaddlePaddle](#gpu) - * **CUDA 工具包 10.1 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高)** + * **CUDA 工具包 10.1 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高; 不支持使用 TensorRT)** * **CUDA 工具包 10.2 配合 cuDNN 7 (cuDNN 版本>=7.6.5, 如需多卡支持，需配合 NCCL2.7 及更高；如需使用 PaddleTensorRT 推理，需配合 TensorRT7.0.0.11)** @@ -89,7 +91,7 @@ * **GPU 运算能力超过 3.5 的硬件设备** - 您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + 您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/tensorrt) * 如果您需要使用多卡环境请确保您已经正确安装 nccl2，或者按照以下指令安装 nccl2（这里提供的是 CUDA10.2，cuDNN7 下 nccl2 的安装指令，更多版本的安装信息请参考 NVIDIA[官方网站](https://developer.nvidia.com/nccl)）: @@ -163,11 +165,16 @@ 2.2.4 CUDA11.2 的 PaddlePaddle - + cuDNN8.1.1: ``` python -m pip install paddlepaddle-gpu==2.4.0rc0.post112 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html ``` + 如果你想使用 PaddleTensorRT 进行推理，cudnn8.2.1 与 TensorRT8.0.3.4 联编的安装包能够获得更优的推理性能，安装命令如下： + ``` + python -m pip install paddlepaddle-gpu==2.4.0rc0.post112 -f https://www.paddlepaddle.org.cn/whl/linux/cuda11.2-cudnn8.2-tensorrt8.html + ``` + 2.2.5 CUDA11.6 的 PaddlePaddle @@ -236,8 +243,6 @@ python -m pip download paddlepaddle==2.4.0rc0 -f https://www.paddlepaddle.org.cn/whl/linux/openblas/avx/stable.html --no-index --no-deps ``` -* 如果你想在`cuda11.2`环境下，获得更好的`PaddleTensorRT`推理性能，需配合`cudnn8.2.1`，并安装联编`tensorrt8.0.3.4`的 Paddle 包，可以参考[下载安装 Linux 预测库](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html)。 - diff --git a/docs/install/pip/linux-pip_en.md b/docs/install/pip/linux-pip_en.md index 9da0d3e6104..221934d1a2b 100644 --- a/docs/install/pip/linux-pip_en.md +++ b/docs/install/pip/linux-pip_en.md @@ -75,7 +75,7 @@ If you installed Python via Homebrew or the Python website, `pip` was installed * If your computer has NVIDIA® GPU, please make sure that the following conditions are met and install [the GPU Version of PaddlePaddle](#gpu) - * **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)** + * **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher; TensorRT is not supported)** * **CUDA toolkit 10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.0.0.11)** @@ -89,7 +89,7 @@ If you installed Python via Homebrew or the Python website, `pip` was installed * **Hardware devices with GPU computing power over 3.5** - You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/tensorrt) * If you need to use a multi-card environment, please make sure that you have installed nccl2 correctly, or install nccl2 according to the following instructions (here are the installation instructions of nccl2 under CUDA10.2 and cuDNN7. For more version installation information, please refer to NVIDIA [Official Website](https://developer.nvidia.com/nccl)): diff --git a/docs/install/pip/macos-pip.md b/docs/install/pip/macos-pip.md index 7d30b0c87e0..b40df5d36ea 100644 --- a/docs/install/pip/macos-pip.md +++ b/docs/install/pip/macos-pip.md @@ -1,5 +1,7 @@ # MacOS 下的 PIP 安装 +The Python Package Index(PyPI)是 Python 的包管理器。本文档为你介绍 PyPI 安装方式。PyPI 下载详见 PyPI 官网（PyPI 官网设置链接：https://pypi.org/）。 + ## 一、环境准备 ### 1.1 目前飞桨支持的环境 diff --git a/docs/install/pip/windows-pip.md b/docs/install/pip/windows-pip.md index f25e72905cd..509c4a87eba 100644 --- a/docs/install/pip/windows-pip.md +++ b/docs/install/pip/windows-pip.md @@ -1,5 +1,7 @@ # Windows 下的 PIP 安装 +The Python Package Index(PyPI)是 Python 的包管理器。本文档为你介绍 PyPI 安装方式，飞桨提供的 PyPI 安装包支持分布式训练（多机多卡）、TensorRT 推理功能；PyPI 下载详见 PyPI 官网（PyPI 官网设置链接：https://pypi.org/）。 + ## 一、环境准备 ### 1.1 目前飞桨支持的环境 @@ -51,7 +53,7 @@ * 如果您的计算机有 NVIDIA® GPU，请确保满足以下条件并且安装 GPU 版 PaddlePaddle - * **CUDA 工具包 10.1 配合 cuDNN v7.6.5** + * **CUDA 工具包 10.1 配合 cuDNN v7.6.5(不支持使用 TensorRT)** * **CUDA 工具包 10.2 配合 cuDNN v7.6.5(如需使用 PaddleTensorRT 推理，需配合 TensorRT7.0.0.11)** @@ -65,7 +67,7 @@ * **GPU 运算能力超过 3.5 的硬件设备** - * 注：目前官方发布的 windows 安装包仅包含 CUDA 10.1/10.2/11.1/11.2/11.6/11.7，如需使用其他 cuda 版本，请通过源码自行编译。您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + * 注：目前官方发布的 windows 安装包仅包含 CUDA 10.1/10.2/11.1/11.2/11.6/11.7，如需使用其他 cuda 版本，请通过源码自行编译。您可参考 NVIDIA 官方文档了解 CUDA、CUDNN 和 TensorRT 的安装流程和配置方法，请见[CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/tensorrt) diff --git a/docs/install/pip/windows-pip_en.md b/docs/install/pip/windows-pip_en.md index dd0b0e5cd55..254a537ca64 100644 --- a/docs/install/pip/windows-pip_en.md +++ b/docs/install/pip/windows-pip_en.md @@ -50,7 +50,7 @@ If you installed Python via Homebrew or the Python website, `pip` was installed * If your computer has NVIDIA® GPU, please make sure that the following conditions are met and install [the GPU Version of PaddlePaddle](#gpu) - * **CUDA toolkit 10.1 with cuDNN v7.6.5** + * **CUDA toolkit 10.1 with cuDNN v7.6.5(TensorRT is not supported)** * **CUDA toolkit 10.2 with cuDNN v7.6.5(for PaddleTensorRT deployment, TensorRT7.0.0.11)** @@ -64,7 +64,7 @@ If you installed Python via Homebrew or the Python website, `pip` was installed * **GPU CUDA capability over 3.5** - You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) + You can refer to NVIDIA official documents for installation process and configuration method of CUDA, cuDNN and TensorRT. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)，[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)，[TensorRT](https://developer.nvidia.com/tensorrt) ## Installation Step From 1ed7ef1ddc13fc878f14dc9781e0b41b3e0e3c42 Mon Sep 17 00:00:00 2001 From: JingZhuangzhuang <75348594+JZZ-NOTE@users.noreply.github.com> Date: Wed, 28 Sep 2022 19:05:19 +0800 Subject: [PATCH 5/5] Update linux-compile_en.md --- docs/install/compile/linux-compile_en.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/install/compile/linux-compile_en.md b/docs/install/compile/linux-compile_en.md index 4770bf1717f..755cfc70667 100644 --- a/docs/install/compile/linux-compile_en.md +++ b/docs/install/compile/linux-compile_en.md @@ -16,7 +16,7 @@ * If your computer has NVIDIA® GPU, and the following conditions are met，GPU version of PaddlePaddle is recommended. - * **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher；TensorRT is not support)** + * **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher；TensorRT is not supported)** * **CUDA toolkit 10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.0.0.11)** * **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT7.2.3.4)** * **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher；for PaddleTensorRT deployment, TensorRT8.0.3.4)**