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.
defilantech/LLMKube
View on GitHub ↗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.
LLMKube grew +14.6% in the last 30 days, ranks 187th of 320 in Production Serving & Deployment, actively maintained, last commit today.
Star trajectory
115 days tracked+14.6% in 30d, above the Production Serving & Deployment median of +1.2%.
Last commit today, fresher than the median of 3d.
How it compares in Production Serving & Deployment
Ranked 187th of 320 by stars.
- Language
- Go
- License
- Apache License 2.0
- Contributors
- 20
- Forks
- 40
- Watchers
- 1
- Open issues
- 119
- Releases
- 299
- Created
- 2025-11-12
- Stars this week
- +9
You've seen where LLMKube stands today.
Get the moves before everyone else: the 5 Production Serving & Deployment repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.