{"work":{"id":"d970e106-3cea-4d01-88f2-f4ffc759b0da","openalex_id":null,"doi":null,"arxiv_id":"2401.08671","raw_key":null,"title":"2024.Deepspeed-fastgen: High-throughput text generation for llms via mii and deepspeed-inference","authors":null,"authors_text":"Connor Holmes, Masahiro Tanaka, Michael Wyatt, Ammar Ah- mad Awan, Jeff Rasley, Samyam Rajbhandari, Reza Yazdani Am- inabadi, Heyang Qin, Arash Bakhtiari, Lev Kurilenko, et al","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2401.08671","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-04T11:59:50.582581+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T09:59:03.462700+00:00","updated_at":"2026-07-04T11:59:50.582581+00:00","title_quality_ok":false,"display_title":"Deepspeed-fastgen: High-throughput text generation for llms via MII and deepspeed-inference","render_title":"Deepspeed-fastgen: High-throughput text generation for llms via MII and deepspeed-inference"},"hub":{"state":{"work_id":"d970e106-3cea-4d01-88f2-f4ffc759b0da","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":24,"external_cited_by_count":null,"distinct_field_count":9,"first_pith_cited_at":"2024-04-22T15:53:08+00:00","last_pith_cited_at":"2026-06-30T20:27:49+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":"2026-08-21T15:49:45.267743+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4}],"polarity_counts":[{"context_polarity":"background","n":4}],"runs":{},"summary":{},"graph":{},"authors":[]}}