[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-scheduling":3},{"tag":4,"articles":9},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":8},"c71a7a69-3473-471c-9244-88d67b7d27cb","scheduling",0,null,[10],{"id":11,"slug":12,"title":13,"summary":14,"category":15,"image_url":16,"cover_image":16,"language":17,"created_at":18},"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"]