[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-inference-cost":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"28e70747-db4a-4095-b5c1-a082bd9f32f5","inference cost","inference-cost",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"7ab95b03-7468-4fef-93bc-0f6f13e61b25","why-routing-is-the-real-bottleneck-in-model-serving-en","Why routing is the real bottleneck in model serving","Routing, not model execution, is the main constraint in modern model serving.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778278838114-82jm.png","en","2026-05-08T22:20:22.905795+00:00"]