{"work":{"id":"04db917c-d1d5-44e1-a54e-280c2f19b98e","openalex_id":null,"doi":null,"arxiv_id":"2401.09670","raw_key":null,"title":"Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving, 2024","authors":null,"authors_text":"Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, and Hao Zhang","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2401.09670","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-25T03:15:17.271429+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T07:47:12.408031+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving","render_title":"Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving"},"hub":{"state":{"work_id":"04db917c-d1d5-44e1-a54e-280c2f19b98e","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":15,"external_cited_by_count":null,"distinct_field_count":6,"first_pith_cited_at":"2024-04-22T15:53:08+00:00","last_pith_cited_at":"2026-05-22T09:00:45+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-11T04:17:37.290493+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2}],"polarity_counts":[{"context_polarity":"background","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}