PaddlePaddle/Serving
Paddle Serving is a serving framework for deploying PaddlePaddle deep learning models as online inference services.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
Paddle Serving provides industrial-grade online inference serving for deep learning models built with PaddlePaddle. It integrates the Paddle Inference engine, supports RESTful, gRPC, and bRPC protocols, and offers deployment solutions across heterogeneous hardware and operating systems. The repository also includes examples for common pre-trained models, though it is no longer maintained in favor of Triton Inference Server.
Frequently asked
- What is PaddlePaddle/Serving?
- Paddle Serving is a serving framework for deploying PaddlePaddle deep learning models as online inference services.
- Is Serving open source?
- Yes — PaddlePaddle/Serving is open source, released under the Apache-2.0 license.
- What language is Serving written in?
- PaddlePaddle/Serving is primarily written in C++.
- How popular is Serving?
- PaddlePaddle/Serving has 925 stars on GitHub.
- Where can I find Serving?
- PaddlePaddle/Serving is on GitHub at https://github.com/PaddlePaddle/Serving.