gpustack by gpustack

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer. Maintained by LMCache on GitHub, where it has earned 11,024 stars from the community.

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers. Maintained by containers on GitHub, where it has earned 2,987 stars from the community.

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines. Maintained by OpenBMB on GitHub, where it has earned 5,713 stars from the community.