[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-ai-推論":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"57bc266d-15a0-45f9-9a95-dfd8af9be803","AI 推論","ai-推論",2,null,[11,20],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"82766fdc-4368-445d-bb4a-03377726df02","turboquant-cuts-memory-use-without-accuracy-loss-zh","TurboQuant 省 6 倍記憶體，還不掉準確率","Google Research 發表 TurboQuant，主打記憶體用量降到 1\u002F6、推論快 8 倍，且在報告測試中沒有準確率損失。這篇看它怎麼改 AI 伺服器成本。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775161134112-ftrj.png","zh","2026-04-02T20:18:39.266389+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"9d1ed0f2-aace-46ce-9b0a-0c0d8655e8e8","turboquant-wont-fix-memory-crunch-zh","TurboQuant 解不了記憶體荒","Google 的 TurboQuant 可把 KV-cache 記憶體用量降到 6 倍，但更長上下文、更多 agent 與更高吞吐，可能把 DRAM 和 NAND 需求繼續往上推。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775132150405-6fvw.png","2026-04-02T12:15:31.810812+00:00"]