# defilantech/LLMKube

<https://repo.masters-masters.com/en/repos/defilantech/LLMKube>

[Home](https://repo.masters-masters.com/en) › [defilantech](https://repo.masters-masters.com/en/owners/defilantech) › [LLMKube](https://repo.masters-masters.com/en/repos/defilantech/LLMKube)

defilantech/LLMKube has 252 stars on GitHub. Its RepoMasters card: Alpha tier. Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU…

| Field | Value |
| --- | --- |
| Owner | [defilantech](https://repo.masters-masters.com/en/owners/defilantech) |
| Stars | 252 |
| Forks | 43 |
| Language | [Go](https://repo.masters-masters.com/en/languages/go) |
| License | Apache-2.0 |
| Created | 2025 |
| Topics | ai, gguf, gpu, inference, kubernetes, kubernetes-operator, llama-cpp, llm, local-llm, nvidia |
| Tier | [Alpha (250 to 699 ★)](https://repo.masters-masters.com/en/ranks/b_movie) |
| View on GitHub | [defilantech/LLMKube](https://github.com/defilantech/LLMKube) |

## Repository

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, active…

The tier for repos with 250 to 699 ★. Published odds per card pulled: 20%. Rarity: Uncommon.

## Nearby in Go

- [yolorouter/yolorouter · ★ 252 · Go · Alpha](https://repo.masters-masters.com/en/repos/yolorouter/yolorouter)
- [akha-security/akca · ★ 252 · Go · Alpha](https://repo.masters-masters.com/en/repos/akha-security/akca)
- [brig-sh/brig · ★ 252 · Go · Alpha](https://repo.masters-masters.com/en/repos/brig-sh/brig)
- [scorredoira/email · ★ 252 · Go · Alpha](https://repo.masters-masters.com/en/repos/scorredoira/email)
- [Debian/dcs · ★ 252 · Go · Alpha](https://repo.masters-masters.com/en/repos/Debian/dcs)
- [thefryscorer/schemer · ★ 252 · Go · Alpha](https://repo.masters-masters.com/en/repos/thefryscorer/schemer)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.