Tag: #LMCache
Kubernetes, DevOps and MLOps, written from things we ran and measured ourselves · 1 posts
vLLM production-stack · LMCache · llm-d: Code map of the engine frontend and KV cache tier
To turn a single vLLM engine into a Kubernetes-native service, you need a frontend (router/gateway), a tier to extend the KV cache beyond the GPU, and metrics connecting the two. This post follows the production-stack Py
2026-10-16 · 40 min read #오픈소스#코드 읽기#vLLM#production-stack#LMCache