Skip to main content

5 docs tagged with "platform-engineering"

View all tags

Field Notes

Production scenario field notes for Kubernetes LLM platforms, covering latency, GPU capacity, RAG tenant isolation, and KServe vs Ray Serve ownership decisions.

K8s LLM: Kubernetes LLM Platform Guide

K8sLLM guide for designing a Kubernetes LLM platform with GPU node pools, vLLM, KServe, Ray Serve, RAG, observability, labs, and reference architectures.

Learning Map

Senior learning map for Kubernetes, platform services, and LLM workloads on Kubernetes.

LLM Production Readiness Checklist

Free Kubernetes LLM production readiness checklist covering GPU placement, serving health, RAG security, observability, rollout, rollback, cost, and ownership.