apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-19 00:48:26 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[Doc] Update download_prebuilt_libraries.md (#541)

Browse Source 
* add paddle_trt in benchmark

* update benchmark in device

* update benchmark

* update result doc

* fixed for CI

* update python api_docs

* update index.rst

* add runtime cpp examples

* deal with comments

* Update infer_paddle_tensorrt.py

* Add runtime quick start

* deal with comments

* fixed reused_input_tensors&&reused_output_tensors

* fixed docs

Co-authored-by: Jason <928090362@qq.com>
This commit is contained in:
WJJ1995
2022-11-09 14:38:50 +08:00
committed by GitHub
parent 070458fc72
commit 581962bcbb
2 changed files with 18 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/cn/build_and_install/download_prebuilt_libraries.md
View File

@@ -1,8 +1,11 @@
# 预编译库安装
FastDeploy提供各平台预编译库，供开发者直接下载安装使用。当然FastDeploy编译也非常容易，开发者也可根据自身需求编译FastDeploy。
本文分为两部分：
- [1.GPU部署环境](##GPU部署环境)
- [2.CPU部署环境](##CPU部署环境)
## GPU部署环境
### 环境要求

25
docs/en/build_and_install/download_prebuilt_libraries.md Normal file → Executable file
View File

@@ -1,8 +1,11 @@
# How to Install Prebuilt Library
FastDeploy provides pre-built libraries for developers to download and install directly. Meanwhile, FastDeploy also offers easy access to compile so that developers can compile FastDeploy according to their own needs.
This article is divided into two parts:
- [1.GPU Deployment Environment](##GPU Deployment Environment)
- [2.CPU Deployment Environment](##CPU Deployment Environment)
## GPU Deployment Environment
### Environment Requirement
@@ -16,10 +19,10 @@ FastDeploy supports Computer Vision, Text and NLP model deployment on CPU and Nv
### Python SDK
Install the released version（the newest 0.4.0 for now）
Install the released version（the newest 0.5.0 for now）
```
pip install fastdeploy-gpu-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html
pip install fastdeploy-gpu-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html
```
Install the Develop version（Nightly build）
@@ -36,12 +39,12 @@ conda config --add channels conda-forge && conda install cudatoolkit=11.2 cudnn=
### C++ SDK
Install the released version（Latest 0.4.0）
Install the released version（Latest 0.5.0）
| Platform | File | Description |
|:----------- |:--------------------------------------------------------------------------------------------------------------------- |:--------------------------------------------------------- |
| Linux x64 | [fastdeploy-linux-x64-gpu-0.4.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.4.0.tgz) | Compiled from g++ 8.2, CUDA 11.2, cuDNN 8.2 |
| Windows x64 | [fastdeploy-win-x64-gpu-0.4.0.zip](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-gpu-0.4.0.zip) | Compiled from Visual Studio 16 2019, CUDA 11.2, cuDNN 8.2 |
| Linux x64 | [fastdeploy-linux-x64-gpu-0.5.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.5.0.tgz) | Compiled from g++ 8.2, CUDA 11.2, cuDNN 8.2 |
| Windows x64 | [fastdeploy-win-x64-gpu-0.5.0.zip](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-gpu-0.5.0.zip) | Compiled from Visual Studio 16 2019, CUDA 11.2, cuDNN 8.2 |
Install the Develop version（Nightly build）
@@ -61,7 +64,7 @@ FastDeploy supports computer vision, text and NLP model deployment on CPU with P
### Python SDK
Install the released version（Latest 0.4.0 for now）
Install the released version（Latest 0.5.0 for now）
```
pip install fastdeploy-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html
@@ -75,15 +78,15 @@ pip install fastdeploy-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fast
### C++ SDK
Install the released version（Latest 0.4.0 for now）
Install the released version（Latest 0.5.0 for now, Android is 0.4.0 pre-release）
| Platform | File | Description |
|:------------- |:--------------------------------------------------------------------------------------------------------------------- |:------------------------------ |
| Linux x64 | [fastdeploy-linux-x64-0.4.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.4.0.tgz) | Compiled from g++ 8.2 |
| Windows x64 | [fastdeploy-win-x64-0.4.0.zip](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-0.4.0.zip) | Compiled from Visual Studio 16 |
| Linux x64 | [fastdeploy-linux-x64-0.5.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.5.0.tgz) | Compiled from g++ 8.2 |
| Windows x64 | [fastdeploy-win-x64-0.5.0.zip](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-win-x64-0.5.0.zip) | Compiled from Visual Studio 16 |
| Mac OSX x64 | [fastdeploy-osx-x86_64-0.4.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-osx-x86_64-0.4.0.tgz) | - |
| Mac OSX arm64 | [fastdeploy-osx-arm64-0.4.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-osx-arm64-0.4.0.tgz) | - |
| Linux aarch64 | [fastdeploy-linux-aarch64-0.2.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-aarch64-0.2.0.tgz) | Compiled from g++ 6.3.0 |
| Linux aarch64 | [fastdeploy-linux-aarch64-0.4.0.tgz](https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-aarch64-0.4.0.tgz) | Compiled from g++ 6.3.0 |
| Android armv7&v8 | [fastdeploy-android-0.4.0-shared.tgz](https://bj.bcebos.com/fastdeploy/release/android/fastdeploy-android-0.4.0-shared.tgz) | Compiled from NDK 25 and clang++, support arm64-v8a and armeabi-v7a |
Install the Develop version（Nightly build）