From e7125580c59e37d14c881d3e453415bcc0acfbb5 Mon Sep 17 00:00:00 2001 From: JZZ-NOTE Date: Wed, 28 Sep 2022 03:45:39 +0000 Subject: [PATCH 1/2] add tensorrt in docs --- docs/install/compile/linux-compile.md | 13 +++++++------ docs/install/compile/linux-compile_en.md | 13 +++++++------ docs/install/pip/linux-pip.md | 16 +++++++++------- docs/install/pip/linux-pip_en.md | 16 +++++++++------- docs/install/pip/windows-pip.md | 16 ++++++++-------- docs/install/pip/windows-pip_en.md | 14 ++++++++------ 6 files changed, 48 insertions(+), 40 deletions(-) diff --git a/docs/install/compile/linux-compile.md b/docs/install/compile/linux-compile.md index 33c55cef511..8cf4d308281 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 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) ## 安装步骤 diff --git a/docs/install/compile/linux-compile_en.md b/docs/install/compile/linux-compile_en.md index 57214a36669..e87b136e8d2 100644 --- a/docs/install/compile/linux-compile_en.md +++ b/docs/install/compile/linux-compile_en.md @@ -16,14 +16,15 @@ * 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 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 and cudnn. 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..3cd639459a7 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 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) * 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..163ada7aa22 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 and cudnn. 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)): @@ -240,7 +242,7 @@ Note： 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 d0186acfc4f..d5c4f26a894 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 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) @@ -168,8 +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)。 - ## **三、验证安装** diff --git a/docs/install/pip/windows-pip_en.md b/docs/install/pip/windows-pip_en.md index 533c765e702..ad7ebdb6183 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 and cudnn. 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 cab5223fac116c1d4163ff6c114a7ca5b6985e25 Mon Sep 17 00:00:00 2001 From: JZZ-NOTE Date: Wed, 28 Sep 2022 04:00:14 +0000 Subject: [PATCH 2/2] add tensorrt install --- docs/install/compile/linux-compile_en.md | 2 +- docs/install/pip/linux-pip_en.md | 2 +- docs/install/pip/windows-pip_en.md | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/install/compile/linux-compile_en.md b/docs/install/compile/linux-compile_en.md index e87b136e8d2..70448cf14a0 100644 --- a/docs/install/compile/linux-compile_en.md +++ b/docs/install/compile/linux-compile_en.md @@ -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 and cudnn. 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/nvidia-tensorrt-download) ## Installation steps diff --git a/docs/install/pip/linux-pip_en.md b/docs/install/pip/linux-pip_en.md index 4678d9163aa..2932aaa6119 100644 --- a/docs/install/pip/linux-pip_en.md +++ b/docs/install/pip/linux-pip_en.md @@ -91,7 +91,7 @@ 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 and cudnn. 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/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_en.md b/docs/install/pip/windows-pip_en.md index 8d74b04cfc5..b830696b417 100644 --- a/docs/install/pip/windows-pip_en.md +++ b/docs/install/pip/windows-pip_en.md @@ -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 and cudnn. 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/nvidia-tensorrt-download) ## Installation Step