[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-ai-inference":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"fc38f553-fad1-4b1d-ae44-c11e20579e1d","AI inference","ai-inference",4,"AI inference 指模型在部署後進行即時推論的過程，重點在延遲、記憶體與算力成本。從住宅型節點、KV cache 壓縮到長上下文下的 DRAM 壓力，都直接影響雲端與邊緣部署的經濟性。","AI inference is the runtime phase where trained models generate outputs in production, so latency, memory footprint, and compute cost matter most. Topics here include home-based inference nodes, KV-cache compression, and how long contexts keep DRAM demand high.",[12],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"7cb40b02-0efe-4451-b86a-7d66f1d8bbc0","spans-mini-ai-data-centers-move-into-homes-zh","Span把 AI 算力搬進住宅","Span 先在 100 戶新屋測試 1.25 MW 的 AI inference 節點。它想把資料中心從年建改成月建，成本也從每 MW 1,500 萬美元壓到約 300 萬美元。","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776341396071-v0i6.png","zh","2026-04-16T12:09:38.258668+00:00"]