xhqing / FATE-Serving

A scalable, high-performance serving system for federated learning models

FATE-Serving

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