Files
FastDeploy/serving/README_CN.md
heliqi 2f73857b2b [Serving]Update images version to 0.6.0 (#594)
* serving images update to 0.6

* serving images update to 0.6

* serving images update to 0.6
2022-11-16 10:11:43 +08:00

45 lines
1.9 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

简体中文 | [English](README_EN.md)
# FastDeploy 服务化部署
## 简介
FastDeploy基于[Triton Inference Server](https://github.com/triton-inference-server/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
``` shell
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](docs/zh_CN/compile.md)
## 其它文档
- [服务化模型目录说明](docs/zh_CN/model_repository.md) (说明如何准备模型目录)
- [服务化部署配置说明](docs/zh_CN/model_configuration.md) (说明runtime的配置选项)
- [服务化部署示例](docs/zh_CN/demo.md)
### 模型示例列表
| 任务场景 | 模型 |
|---|---|
| Classification | [PaddleClas](../examples/vision/classification/paddleclas/serving/README.md) |
| Detection | [ultralytics/YOLOv5](../examples/vision/detection/yolov5/serving/README.md) |
| NLP | [PaddleNLP/ERNIE-3.0](../examples/text/ernie-3.0/serving/README.md)|
| Speech | [PaddleSpeech/PP-TTS](../examples/audio/pp-tts/serving/README.md)|