https://github.com/FederatedAI/FATE-Serving
A scalable, high-performance serving system for federated learning models
https://github.com/FederatedAI/FATE-Serving
federated-learning inference model-serving model-versioning monitor
Last synced: about 2 months ago
JSON representation
A scalable, high-performance serving system for federated learning models
- Host: GitHub
- URL: https://github.com/FederatedAI/FATE-Serving
- Owner: FederatedAI
- License: apache-2.0
- Created: 2019-09-10T05:58:17.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2024-11-07T02:59:22.000Z (about 1 year ago)
- Last Synced: 2024-11-07T03:29:41.628Z (about 1 year ago)
- Topics: federated-learning, inference, model-serving, model-versioning, monitor
- Language: Java
- Homepage:
- Size: 28.8 MB
- Stars: 139
- Watchers: 30
- Forks: 77
- Open Issues: 23
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- Awesome-FL - FATE-Serving - Serving.svg?color=blue)](https://github.com/FederatedAI/FATE-Serving/stargazers)<br /> | | [WeBank](https://fedai.org/) | | | [[DOC](https://fate-serving.readthedocs.io/en/develop/)] | (federated learning framework / table)
- awesome-java - FATE Serving
README
# FATE-Serving
[](https://opensource.org/licenses/Apache-2.0)
[](https://checkstyle.sourceforge.io/google_style.html)
[](https://checkstyle.sourceforge.io/google_style.html)
## Introduction
FATE-Serving is a high-performance, industrialized serving system for federated learning models, designed for production environments.
### FATE-Serving now supports
- High performance online Federated Learning algorithms.
- Real-time inference using federated learning models.
- Support parallel inference between guest and host.
- Support parallel computing in a inference request.
- Provide service managerment for grpc interface by using zookeeper as registry.
- Visualization tools are provided for cluster management and model management.
### document
[document](https://fate-serving.readthedocs.io/en/develop/)