[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-qjl":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"c33d75f2-b23d-4140-97db-74624f4db775","QJL","qjl",2,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"6ea121bb-a78e-4bc2-bda3-9be1e048ab95","googles-turboquant-cuts-llm-memory-costs-zh","Google TurboQuant 壓低 LLM 記憶體成本","Google 推出 TurboQuant，結合 QJL 與 PolarQuant，主打壓低 vector quantization 的記憶體開銷，並宣稱 LLM inference 最高可快 8 倍。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775160769707-5e2g.png","zh","2026-04-02T20:12:31.803679+00:00"]