All
Articles 106,850Blog Posts 118,664Tech Tutorials 26,960Research Papers 22,412News 16,353
⚡ AI Lessons
Dev.to · Pavan Madduri
19h ago
Serving 3 LLMs on 1 GPU - Multi-Model Inference with Docker on OKE
I had three small models I wanted to serve: Phi-3-mini for general chat, CodeLlama-7B for code...
Dev.to · Pavan Madduri
☁️ DevOps & Cloud
⚡ AI Lesson
1d ago
Docker Build Cloud Cut My CI Build Times by 75%, Here's How I Wired It to OCIR
My GPU inference image was 8GB. Building it in GitHub Actions took 14 minutes on the free runner....
Dev.to · Pavan Madduri
2d ago
How I Run GPU Workloads for 70% Less on OKE Using Preemptible Instances
I was spending ~$3,300/month on three A10 GPU instances for a mix of staging inference, batch...
Dev.to · Pavan Madduri
3d ago
Running Ollama on OCI Container Instances - Private LLM API in 5 Minutes, No Kubernetes
A colleague asked me to set up a private LLM endpoint their team could use for code review...
Dev.to · Pavan Madduri
☁️ DevOps & Cloud
⚡ AI Lesson
1w ago
Zero-Downtime Crossplane v1 v2 Migration: Adopt-in-Place at Production Scale
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
Dev.to · Pavan Madduri
☁️ DevOps & Cloud
⚡ AI Lesson
1w ago
docker init OCIR OKE: From Empty Folder to Production in 15 Minutes
I timed myself. Starting from an empty directory with a Go application idea, how fast could I get to...
Dev.to · Pavan Madduri
⚡ AI Lesson
2w ago
I Stopped Paying for Idle GPUs - Scale-to-Zero AI Inference on OKE with KEDA
A single A10 GPU on OCI costs $1.52/hr. Running 24/7, that's $1,094/month. For a production inference...
Dev.to · Pavan Madduri
🧠 Large Language Models
⚡ AI Lesson
2w ago
Deploying vLLM on OKE with NVIDIA A10 GPUs: The 20-Minute Setup Nobody Talks About
Last month I needed to stand up a Llama 3 inference endpoint for an internal tool. The requirements...
Dev.to · Pavan Madduri
🏭 MLOps & LLMOps
⚡ AI Lesson
2w ago
Stop Downloading 8GB Models on Every Pod Restart - Use OCI Object Storage as a Model Cache
The first time I deployed vLLM on OKE, the pod took 12 minutes to become ready. The model download...
Dev.to · Pavan Madduri
1mo ago
Docker Model Runner Replaced My Entire Local AI Setup
I used to have a ridiculous local AI setup. Ollama running as a service. A separate Python venv for...
Dev.to · Pavan Madduri
1mo ago
Every GPU Container Bug I've Hit on OKE (and How I Fixed Them)
Running GPU containers on Kubernetes is one of those things that works perfectly in tutorials and...
Dev.to · Pavan Madduri
☁️ DevOps & Cloud
⚡ AI Lesson
1mo ago
From Docker Compose on My Laptop to OKE in Production — Same App, Zero Rewrites
I have a rule: if I can't run the full stack on my laptop with docker compose up, the architecture is...
Dev.to · Pavan Madduri
1mo ago
I Cut My Container Image Costs 60% by Building Multi-Arch Docker Images on OCI ARM
I was running all my containers on AMD64 shapes because that's what I'd always done. x86, Intel/AMD,...
Dev.to · Pavan Madduri
🔐 Cybersecurity
⚡ AI Lesson
1mo ago
The Zero-Trust Docker Pipeline: Securing GPU/AI Container Images from Build to Production
GPU container images are the softest target in your infrastructure. A typical vLLM image is 15GB with...
Dev.to · Pavan Madduri
☁️ DevOps & Cloud
⚡ AI Lesson
1mo ago
GPU-Aware Autoscaling for Docker Containers: From NVML to Production
Every GPU inference container has the same problem: Kubernetes HPA can't see the GPU. You scale on...
Dev.to · Pavan Madduri
⚡ AI Lesson
1mo ago
I Replaced a $3/hr GPU Dev Workflow with Docker Model Runner. Here's How
Last month I was debugging a prompt template for a vLLM inference service. The change was two lines —...
Dev.to · Pavan Madduri
☁️ DevOps & Cloud
⚡ AI Lesson
1mo ago
Docker + OKE: Running GPU Inference Containers on Oracle Cloud
I wanted to deploy an LLM inference API without spending $1,200/month on AWS GPU instances. OCI...
Dev.to · Pavan Madduri
☁️ DevOps & Cloud
⚡ AI Lesson
1mo ago
Running Docker Containers on OCI Without Kubernetes
I needed to run a container in the cloud. Not a microservices platform. Not a service mesh. Just one...
Dev.to · Pavan Madduri
⚡ AI Lesson
3mo ago
Deploying a Production-Ready K3s Cluster on OCI Always Free ARM Instances
Deploying a Production-Ready K3s Cluster on OCI Always Free ARM Instances How I turned...
Dev.to · Pavan Madduri
⚡ AI Lesson
3mo ago
Why Your Kubernetes Cluster Breaks 18 Minutes After a Successful Deployment
You merge the Pull Request. The CI/CD pipeline flashes green. ArgoCD reports that your application is...
DeepCamp AI