Tag: ollama

Apr 23, 2026 · Jakub · DevOps
Running Ollama on EKS: A Production-Grade LLM Setup with a Custom Helm Chart
GPU nodes on demand, zero cost at night, models that survive restarts — how I deployed self-hosted Ollama on Amazon EKS using a single Helm chart with Karpenter, KEDA, and ArgoCD.
Apr 22, 2026 · Jakub · DevOps
Self-hosted AI Stack on AWS EKS: Ollama + LiteLLM + Open WebUI
How I deployed a production-ready, self-hosted LLM stack on Kubernetes using Helm, Karpenter, and KEDA — with GPU auto-scaling and SSO out of the box.