{"type":"link","version":"1.0","title":"Managed LLM serving that cuts GPU costs 2-4x via KV paging","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/biz-paged-kv-cache-serving-infra","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}