Halfrost-Field by halfrost

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc. Maintained by mostlygeek on GitHub, where it has earned 5,268 stars from the community.

A programmable Mixture-of-Models router for heterogeneous LLM inference. Maintained by vllm-project on GitHub, where it has earned 5,116 stars from the community.

AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text. Maintained by kubeai-project on GitHub, where it has earned 1,238 stars from the community.