[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-記憶體頻寬":3},{"tag":4,"articles":9},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":8},"6bc7ce73-c8a7-41c0-9d83-32cdca2e2ff9","記憶體頻寬",1,null,[10],{"id":11,"slug":12,"title":13,"summary":14,"category":15,"image_url":16,"cover_image":16,"language":17,"created_at":18},"fdb08bdf-a3bd-4c4d-acaf-ce8035f24449","turboquant-google-paper-explained-zh","TurboQuant 是什麼？Google 新論文重點","Google 的 TurboQuant 盯上 LLM 的 KV cache 瓶頸，用低位元量化降低記憶體用量與推論成本。這篇帶你看它在解什麼問題、和其他優化法差在哪。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775160957331-6iua.png","zh","2026-04-02T20:15:40.07166+00:00"]