I wanted my own LLM inference setup on bare metal — GPU-backed K8s, autoscaling that actually works with vLLM metrics, and auth so random internet people can’t drain my GPU credits. Here’s how it went.
Why This Guide Exists You’re on Fedora 42. You want a Debian 13 VM — not through some GUI wizard, but properly, from the command line, with real bridged networking so the VM sits on your LAN like a first-class citizen. You want cloud-init to set up your users and passwords. And then you want to turn that VM into a multi-node Kubernetes cluster with podman and minikube. Every guide I found either stopped at “install the VM” or assumed you already knew the networking parts. This one doesn’t. It holds your hand from dnf install to kubectl get nodes. ...
Coming… 💬 Show Comments
A veteran sys admins journal on changes that has come around and being a devops
Hands-on exploration of cluster provisioning, network isolation, and tenant automation in a lab-scale Kubernetes setup.
End-to-end exploration of deploying and federating OpenStack clusters for multi-tenant compute and inference use cases.