njhill - Overview

Pinned Loading

1. A high-throughput and memory-efficient inference and serving engine for LLMs

   Python 83.4k 18.3k

2. IBM development fork of https://github.com/huggingface/text-generation-inference

   Python 65 35

3. Alternative etcd3 java client

   Java 163 42

4. Distributed Model Serving Framework

   Java 188 79

5. Netty project - an event-driven asynchronous network application framework

   Java 35k 16.3k

6. Abstracted helper classes providing consistent key-value store functionality, with zookeeper and etcd3 implementations

   Java 6 3