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

Minimalist ML framework for Rust

Fast inference engine for Transformer models

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.