mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00

Files

Thomas Young afe8444782 Add doc for serving (#730 )

* add ocr serving example

* 1

1

* Add files via upload

* Update README.md

* Delete ocr_pipeline.png

* Add files via upload

* Delete ocr_pipeline.png

* Add files via upload

* 1

1

* 1

1

* Update README.md

* 1

1

* fix codestyle

* fix codestyle

* Update README_CN.md

* Update README_EN.md

* Update demo.md

* Update demo.md

* Add files via upload

* Update demo.md

* Add files via upload

* Delete dynamic_batching.png

* Delete instance_group.png

* Delete simple_ensemble.png

* Add files via upload

* Update demo.md

* Update demo.md

* Update demo.md

* Update demo.md

* Delete dynamic_batching.png

* Delete instance_group.png

* Delete simple_ensemble.png

* Update demo.md

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: heliqi <1101791222@qq.com>

2022-11-28 19:49:18 +08:00

2.0 KiB

Raw Blame History

简体中文 | English

FastDeploy 服务化部署

简介

FastDeploy基于Triton Inference Server搭建了端到端的服务化部署。底层后端使用FastDeploy高性能Runtime模块，并串联FastDeploy前后处理模块实现端到端的服务化部署。具有快速部署、使用简单、性能卓越的特性。

准备环境

环境要求

Linux
如果使用GPU镜像，要求NVIDIA Driver >= 470(如果是旧的Tesla架构GPU，如T4使用的NVIDIA Driver可以是418.40+、440.33+、450.51+、460.27+)

获取镜像

CPU镜像

CPU镜像仅支持Paddle/ONNX模型在CPU上进行服务化部署，支持的推理后端包括OpenVINO、Paddle Inference和ONNX Runtime

docker pull paddlepaddle/fastdeploy:0.6.0-cpu-only-21.10

GPU镜像

GPU镜像支持Paddle/ONNX模型在GPU/CPU上进行服务化部署，支持的推理后端包括OpenVINO、TensorRT、Paddle Inference和ONNX Runtime

docker pull paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10

用户也可根据自身需求，参考如下文档自行编译镜像

FastDeploy服务化部署镜像编译说明

其它文档

模型仓库目录说明 (说明如何准备模型仓库目录)
模型配置说明 (说明runtime的配置选项)

服务化部署示例

任务场景	模型
Classification	PaddleClas
Detection	PaddleDetection
Detection	ultralytics/YOLOv5
NLP	PaddleNLP/ERNIE-3.0
NLP	PaddleNLP/UIE
Speech	PaddleSpeech/PP-TTS
OCR	PaddleOCR/PP-OCRv3

2.0 KiB Raw Blame History Unescape Escape