Back to trending
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.
Go157 stars25 forksApache-2.0
aiapple-siliconautoscalingedge-computingggufgpuhomelabinferencekuberneteskubernetes-operatorllama-cppllmlocal-llmmetalmlxmulti-gpunvidiaself-hostedtgivllm
Rankings
Daily
#26540
0
Weekly
#2709
7
Monthly
#11088
1
Engagement
Total stars
Daily new stars
Embed suite
Live embeds for your README
This repository is tracked by Trending Repos. Every embed updates itself — and the badge upgrades to a medal tier the moment you crack the top 100. Set it once and forget it.
- ✓ Live star count, refreshed every 4 hours
- ✓ Medal tiers — gold, silver, bronze
- ✓ Best-ever rank, never downgrades
- ✓ Animated (respects reduced-motion)
- ✓ Free, no sign-up
The badge — your medal
Animated rank-tier badge with your live star count built in. Starts bronze, upgrades automatically the moment your repo climbs — gold at #1, silver top-3, bronze top-10. Shows your best-ever rank, permanently.
Markdown — paste into your README
[](https://trending-repos.com/repositories/defilantech/LLMKube?utm_source=github&utm_medium=badge)The card — your scorecard
Compact momentum card: stars, recent velocity, a 14-day sparkline and your rank tier. The at-a-glance proof your project is moving.
Markdown — paste into your README
[](https://trending-repos.com/repositories/defilantech/LLMKube?utm_source=github&utm_medium=card)The chart — your proof
A live star-growth chart that replaces static screenshots forever. Light and dark variants; GitHub picks the right one automatically with the HTML snippet.
