A reactive data store & sync engine.
A lightweight, lightning-fast, in-process vector database
a stream-based file storage solution for machine learning datasets.
Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library
Bub it. Build it. A tiny agent runtime, composable with plugins.
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
A high-throughput and memory-efficient inference and serving engine for LLMs