https://github.com/jpmcb/ollama-kubernetes-operator

🦙 A Kubernetes operator for Ollama
https://github.com/jpmcb/ollama-kubernetes-operator

kubernetes kubernetes-deployment llama llm ollama rust

Last synced: 9 months ago
JSON representation

🦙 A Kubernetes operator for Ollama

• Host: GitHub
• URL: https://github.com/jpmcb/ollama-kubernetes-operator
• Owner: jpmcb
• Created: 2024-04-20T15:54:49.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-04-20T23:36:31.000Z (about 2 years ago)
• Last Synced: 2025-09-16T00:39:20.457Z (9 months ago)
• Topics: kubernetes, kubernetes-deployment, llama, llm, ollama, rust
• Language: Rust
• Homepage:
• Size: 14.6 KB
• Stars: 5
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 🦙 Ollama-Kubernetes-Operator

A Kubernetes operator to simplify deploying Ollama as GPU workloads to the right nodes.

_A current work in progress._

### Why?

There's no definitive way to deploy Ollama onto a subset of nodes that support

fast, GPU workloads. You can piece-meal it together, but you end up with alot of

tainted deployments with a mess of labels that's difficult to maintain.

The aim of the Ollama-Kubernetes-Operator is to enable Kubernetes practitioners

to easily deploy open source LLM technologies

as a service to their clusters with as minimal maintenance as possible.