DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
最近更新: 8个月前Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
最近更新: 8个月前面向燧原GCU平台的大语言模型推理与聊天服务框架,其基于 Candle-GCU 和 开源项目Candle-vLLM 实现,兼容OpenAI API接口。
最近更新: 8个月前