mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
9e20dab0d6
* fix infer.py and README * [Example] Merge Download Paddle Model, Paddle->Onnx->Mlir->Bmodel and inference into infer.py. Modify README.md * modify pp_liteseg sophgo infer.py and README.md * fix PPOCR,PPYOLOE,PICODET,LITESEG sophgo infer.py and README.md * fix memory overflow problem while inferring with sophgo backend * fix memory overflow problem while inferring with sophgo backend --------- Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com> Co-authored-by: xuyizhou <yizhou.xu@sophgo.com>
PaddleOCR高性能全场景模型部署方案—FastDeploy
目录
1. FastDeploy介绍
⚡️FastDeploy是一款全场景、易用灵活、极致高效的AI推理部署工具，支持云边端部署.使用FastDeploy可以简单高效的在X86 CPU、NVIDIA GPU、飞腾CPU、ARM CPU、Intel GPU、昆仑、昇腾、算能、瑞芯微等10+款硬件上对PaddleOCR模型进行快速部署，并且支持Paddle Inference、Paddle Lite、TensorRT、OpenVINO、ONNXRuntime、SOPHGO、RKNPU2等多种推理后端.
2. PaddleOCR模型部署
2.1 硬件支持列表
| 硬件类型 | 该硬件是否支持 | 使用指南 | Python | C++ |
|---|---|---|---|---|
| X86 CPU | ✅ | 链接 | ✅ | ✅ |
| NVIDIA GPU | ✅ | 链接 | ✅ | ✅ |
| 飞腾CPU | ✅ | 链接 | ✅ | ✅ |
| ARM CPU | ✅ | 链接 | ✅ | ✅ |
| Intel GPU(集成显卡) | ✅ | 链接 | ✅ | ✅ |
| Intel GPU(独立显卡) | ✅ | 链接 | ✅ | ✅ |
| 昆仑 | ✅ | 链接 | ✅ | ✅ |
| 昇腾 | ✅ | 链接 | ✅ | ✅ |
| 算能 | ✅ | 链接 | ✅ | ✅ |
| 瑞芯微 | ✅ | 链接 | ✅ | ✅ |
2.2. 详细使用文档
- X86 CPU
- NVIDIA GPU
- 飞腾CPU
- ARM CPU
- Intel GPU
- 昆仑 XPU
- 昇腾 Ascend
- 算能 Sophgo
- 瑞芯微 Rockchip
2.3 更多部署方式
3. 常见问题
遇到问题可查看常见问题集合，搜索FastDeploy issue，或给FastDeploy提交issue: