[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-token-prediction":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"10b7717d-b316-4725-931d-f4dd58f486d7","token prediction","token-prediction",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"407ca117-f24b-4ff9-96b8-09d4d4733b31","taming-black-box-llm-inference-scheduling-en","Taming Black-Box LLM Inference Scheduling","A scheduling approach for black-box LLM inference that uses predicted output lengths to reduce queueing friction at scale.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778740250597-fhpf.png","en","2026-05-14T06:30:33.21401+00:00"]