@aditmodi24

Generative AI on Kubernetes — Book Review

12h ago · 7 min read · There's a specific kind of frustration that comes from reading a book that's half about what you actually needed. Most resources on running AI in production either assume you're a data scientist who p

NVIDIA's Two Gifts to Kubernetes: DRA and AICR — What They Mean for Your EKS GPU Platform

1d ago · 18 min read · From integer counting to structured resources — how Dynamic Resource Allocation and the AI Cluster Readiness framework finally make GPU infrastructure manageable at scale. Contents The Two Nightmares

AMAdit Modicloudtech.hashnode.dev

👋 Everything about EKS & AI Infrastructure Newsletter "#62" ☁️❤👨‍💻

2d ago · 16 min read · Dear EKS & AI Infrastructure enthusiasts,Welcome to Everything about EKS & AI Infrastructure #62. There’s something uncomfortable happening in AI infrastructure right now that nobody says out loud: th

llm-d on EKS: The New Inference Resource Model That Changes How You Think About GPU Routing

Mar 28 · 27 min read · Your vLLM cluster has a problem you probably don't know about. It's not a bug. Nothing is crashing. The metrics dashboard looks fine. But right now, every time a request hits your load balancer, there

GPU Deadlock on EKS: What Gang Scheduling Actually Is, Why the Default Scheduler Fails You, and Three Ways to Fix It

Mar 28 · 30 min read · There's a class of production incident that doesn't page anyone. No error rate spikes. No latency alert fires. The cluster health dashboard shows green. GPU nodes are online. Pods are running. And yet