简体中文 | English
FastDeploy builds an end-to-end serving deployment based on Triton Inference Server. The underlying backend uses the FastDeploy high-performance Runtime module and integrates the FastDeploy pre- and post-processing modules to achieve end-to-end serving deployment. It can achieve fast deployment with easy-to-use process and excellent performance.
FastDeploy also provides an easy-to-use Python service deployment method, refer PaddleSeg deployment example for its usage.
- Linux
- If using a GPU image, NVIDIA Driver >= 470 is required (for older Tesla architecture GPUs, such as T4, the NVIDIA Driver can be 418.40+, 440.33+, 450.51+, 460.27+)
CPU images only support Paddle/ONNX models for serving deployment on CPUs, and supported inference backends include OpenVINO, Paddle Inference, and ONNX Runtime
docker pull registry.baidubce.com/paddlepaddle/fastdeploy:1.0.4-cpu-only-21.10GPU images support Paddle/ONNX models for serving deployment on GPU and CPU, and supported inference backends including OpenVINO, TensorRT, Paddle Inference, and ONNX Runtime
docker pull registry.baidubce.com/paddlepaddle/fastdeploy:1.0.4-gpu-cuda11.4-trt8.5-21.10
Users can also compile the image by themselves according to their own needs, referring to the following documents:
- How to Prepare Serving Model Repository
- Serving Deployment Configuration for Runtime
- Demo of Serving Deployment
- Client Access Instruction
- Serving deployment visualization
| Task | Model |
|---|---|
| Classification | PaddleClas |
| Detection | PaddleDetection |
| Detection | ultralytics/YOLOv5 |
| NLP | PaddleNLP/ERNIE-3.0 |
| NLP | PaddleNLP/UIE |
| Speech | PaddleSpeech/PP-TTS |
| OCR | PaddleOCR/PP-OCRv3 |