📰 Dev.to · Pavan Madduri

How we moved a production EKS fleet from Crossplane v1 claims/composites to v2 namespaced XRs with no resource recreation, no node rotation, and no downtime — p

I timed myself. Starting from an empty directory with a Go application idea, how fast could I get to...

A single A10 GPU on OCI costs $1.52/hr. Running 24/7, that's $1,094/month. For a production inference...

Last month I needed to stand up a Llama 3 inference endpoint for an internal tool. The requirements...

The first time I deployed vLLM on OKE, the pod took 12 minutes to become ready. The model download...

I used to have a ridiculous local AI setup. Ollama running as a service. A separate Python venv for...

Running GPU containers on Kubernetes is one of those things that works perfectly in tutorials and...

I have a rule: if I can't run the full stack on my laptop with docker compose up, the architecture is...

I was running all my containers on AMD64 shapes because that's what I'd always done. x86, Intel/AMD,...

GPU container images are the softest target in your infrastructure. A typical vLLM image is 15GB with...

Every GPU inference container has the same problem: Kubernetes HPA can't see the GPU. You scale on...

Last month I was debugging a prompt template for a vLLM inference service. The change was two lines —...

I wanted to deploy an LLM inference API without spending $1,200/month on AWS GPU instances. OCI...

I needed to run a container in the cloud. Not a microservices platform. Not a service mesh. Just one...

Deploying a Production-Ready K3s Cluster on OCI Always Free ARM Instances How I turned...

You merge the Pull Request. The CI/CD pipeline flashes green. ArgoCD reports that your application is...