mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-07 09:31:35 +08:00

* RKNPU2 Backend兼容其他模型的量化 fd_tensor正式移除zp和scale的量化参数 * 更新FP32返回值的RKYOLO * 更新rkyolov5支持fp32格式 * 更新rkyolov5支持fp32格式 * 更新YOLOv5速度文档 Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
简体中文| English
Tutorials
Install
- Install FastDeploy Prebuilt Libraries
- Build and Install FastDeploy Library on GPU Platform
- Build and Install FastDeploy Library on CPU Platform
- Build and Install FastDeploy Library on IPU Platform
- Build and Install FastDeploy Library on KunlunXin XPU Platform
- Build and Install FastDeploy Library on Nvidia Jetson Platform
- Build and Install FastDeploy Library on Android Platform
- Build and Install FastDeploy Serving Deployment Image
A Quick Start - Demos
- Python Deployment Demo
- C++ Deployment Demo
- A Quick Start on Runtime Python
- A Quick Start on Runtime C++
API
Performance Optimization
Frequent Q&As
- 1. How to Change Inference Backends
- 2. How to Use FastDeploy C++ SDK on Windows Platform
- 3. How to Use FastDeploy C++ SDK on Android Platform
- 4. Tricks of TensorRT
- 5. How to Develop a New Model