LLMKube

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed. Maintained by defilantech on GitHub, where it has earned 185 stars from the community.

It's actively developed around ai, gguf, gpu, and is a solid reference for anyone building with these tools.