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.

Last push 3 hours ago

Created

Nov 2025

Total stars

267

7 days

+1

30 days

+30

12 months

+264

Star trends

README badge

Best of Go badge for defilantech/LLMKube
[![Best of Go](https://bestofgo.dev/badge/defilantech/LLMKube.svg)](https://bestofgo.dev/defilantech/LLMKube)