Topic Hub

DevOps & Platform

CI/CD, GitOps, IaC, and the platform-engineering playbook.

GitOps with Argo and Flux, Terraform, GitHub Actions, platform engineering patterns, and the build/test/deploy pipeline that ships modern apps.

Start here

More on DevOps & Platform

Cover for Running a big LLM across multiple GPUs with vLLM
vllmgpuAug 18, 2026

Running a big LLM across multiple GPUs with vLLM

A plain-English guide to serving a model too big for one GPU, in two tracks: a runbook from download to serving with every flag and error explained, and a deep dive into how tensor, pipeline, and expert parallelism split the model, with measured numbers from a 235B model on four RTX PRO 6000 cards.

Shubham KataraSaiyam Pathak
Shubham Katara & Saiyam Pathak · 52 min
Read →
Cover for I Ran an AI SRE Copilot on My Own Hardware. Here Is What It Actually Does.
kubernetesaiAug 17, 2026

I Ran an AI SRE Copilot on My Own Hardware. Here Is What It Actually Does.

Running NudgeBee v1.4.0 end to end - a self-hosted AIOps platform behind AI-SRE, AI-FinOps, AI-K8sOps, and agentic automation - on a Mac, a kiac cluster, and a DGX Spark.

Saiyam Pathak
Saiyam Pathak · 21 min
Read →
Cover for HAMi Dynamic MIG on RTX PRO 6000: A Live Kubernetes Test
kubernetesgpuAug 11, 2026

HAMi Dynamic MIG on RTX PRO 6000: A Live Kubernetes Test

Hands-on HAMi Dynamic MIG test on Kubernetes and RTX PRO 6000 Blackwell: setup commands, real allocations, mixed profiles, reclamation, and recovery.

Shubham KataraSaiyam Pathak
Shubham Katara & Saiyam Pathak · 24 min
Read →
Cover for Devin Outposts on Kubernetes: Why Your AI Agent Needs Your Cluster
kubernetesai-agentsAug 10, 2026

Devin Outposts on Kubernetes: Why Your AI Agent Needs Your Cluster

Devin Outposts runs AI coding agent sessions as pods on your own Kubernetes cluster, with an open-source operator to manage the fleet.

Saiyam Pathak
Saiyam Pathak · 11 min
Read →
Cover for How to Share GPUs in Kubernetes at Scale with HAMi (Software vGPU Slicing)
kubernetesgpuJul 23, 2026

How to Share GPUs in Kubernetes at Scale with HAMi (Software vGPU Slicing)

Share NVIDIA GPUs in Kubernetes with HAMi software vGPU slicing: memory and compute limits, Helm configuration, a verified PyTorch manifest, a real RTX PRO 6000 OOM test, and Prometheus monitoring.

Shubham KataraSaiyam Pathak
Shubham Katara & Saiyam Pathak · 34 min
Read →
Cover for Slicing GPUs in Kubernetes with NVIDIA Multi-Instance GPU (MIG)
kubernetesgpuJul 20, 2026

Slicing GPUs in Kubernetes with NVIDIA Multi-Instance GPU (MIG)

GPU sharing in Kubernetes explained: time-slicing vs MPS vs MIG, every nvidia-smi command to enable and disable MIG on one GPU or eight, GPU Operator automation, pitfalls, and DCGM monitoring.

Shubham KataraSaiyam Pathak
Shubham Katara & Saiyam Pathak · 45 min
Read →
Cover for Controlling MCP Tools with agentgateway on Kubernetes (Part 1)
kubernetesai-agentsJun 29, 2026

Controlling MCP Tools with agentgateway on Kubernetes (Part 1)

Run AI agents behind agentgateway on Kubernetes: route their LLM and MCP tool calls through one proxy, keep secrets out of the agent, and block tools by policy.

Shubham Katara
Shubham Katara · 22 min
Read →
Cover for How Kubernetes EndpointSlices Actually Work (and Why Endpoints Had to Die)
kubernetesdevopsMay 11, 2026

How Kubernetes EndpointSlices Actually Work (and Why Endpoints Had to Die)

A Service has no pod IPs in it. We covered that in the last post. So somewhere, something is keeping a list of every pod IP that matches the Service's…

Saiyam Pathak
Saiyam Pathak · 12 min
Read →
Cover for How a Kubernetes Service Actually Works (and All 5 Types You Need)
kubernetesserviceMay 5, 2026

How a Kubernetes Service Actually Works (and All 5 Types You Need)

A pod gets created. It gets an IP. Then it dies. A new pod replaces it. New IP. Now imagine you have ten pods of the same app, and they restart all the…

Saiyam Pathak
Saiyam Pathak · 13 min
Read →
Cover for Day 7: Ship It - and What Comes Next
dockersecurityMay 4, 2026

Day 7: Ship It - and What Comes Next

Your container runs as root and has 18 CVEs. A Docker Captain's guide to hardening, Scout policies, DHI, Sandboxes, and what comes after Docker.

Saloni Narang
Saloni Narang · 13 min
Read →
Cover for Day 6: Run an LLM on Your Laptop - With Docker
aidockerApr 30, 2026

Day 6: Run an LLM on Your Laptop - With Docker

"Pull AI models from Docker Hub, run them locally with GPU acceleration, and build an AI-powered app

Saloni Narang
Saloni Narang · 10 min
Read →
Cover for What Actually Happens When kube-scheduler Picks a Node (13 Stages Inside Kubernetes)
kubernetesdevopsApr 28, 2026

What Actually Happens When kube-scheduler Picks a Node (13 Stages Inside Kubernetes)

How kube-scheduler picks a node: 13 framework stages, 14 Filter plugins, 9 Score plugins, live preemption demo.

Saiyam Pathak
Saiyam Pathak · 22 min
Read →
Show 68 more DevOps & Platform articles