{"id":"https://openalex.org/W4415250873","doi":"https://doi.org/10.1109/hpec67600.2025.11196629","title":"Predicting LLM Inference Server Request Capacity","display_name":"Predicting LLM Inference Server Request Capacity","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4415250873","doi":"https://doi.org/10.1109/hpec67600.2025.11196629"},"language":"en","primary_location":{"id":"doi:10.1109/hpec67600.2025.11196629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078723372","display_name":"Daniel J. Burrill","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel J. Burrill","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109794511","display_name":"Larry W. Anderson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"LaToya Anderson","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030983536","display_name":"William Arcand","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Arcand","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072368385","display_name":"David Bestor","orcid":"https://orcid.org/0009-0002-7684-1191"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Bestor","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059180282","display_name":"William Bergeron","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Bergeron","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114387277","display_name":"Alex Bonn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Bonn","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087896681","display_name":"Chansup Byun","orcid":"https://orcid.org/0009-0003-0183-914X"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chansup Byun","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025538864","display_name":"Michael E. Houle","orcid":"https://orcid.org/0000-0001-8486-8015"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Houle","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083823664","display_name":"Matthew Hubbell","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Hubbell","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935573","display_name":"Michael G. Jones","orcid":"https://orcid.org/0000-0002-5434-4904"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Jones","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Luszczek","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112526610","display_name":"Peter Michaleas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Michaleas","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091208564","display_name":"Guillermo Morales","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guillermo Morales","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059111534","display_name":"Julie Mullen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie Mullen","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103257220","display_name":"Andrew Prout","orcid":"https://orcid.org/0000-0002-4408-0247"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Prout","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000293770","display_name":"Albert Reuther","orcid":"https://orcid.org/0000-0002-3168-3663"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert Reuther","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043926638","display_name":"Antonio De Rosa","orcid":"https://orcid.org/0000-0002-1392-4881"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Rosa","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110423798","display_name":"Charles Yee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Yee","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102979602","display_name":"Vijay Gadepally","orcid":"https://orcid.org/0009-0004-5782-7137"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Gadepally","raw_affiliation_strings":["MIT Lincoln Laboratory,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,MA","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":19,"corresponding_author_ids":["https://openalex.org/A5078723372"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36695276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9053000211715698,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9053000211715698,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.6139000058174133},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6136999726295471},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5708000063896179},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4422000050544739},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.4097999930381775},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.38960000872612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767300009727478},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.6139000058174133},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C2781007418","wikidata":"https://www.wikidata.org/wiki/Q1456934","display_name":"Capacity planning","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C55350006","wikidata":"https://www.wikidata.org/wiki/Q237193","display_name":"Exponential distribution","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C9930424","wikidata":"https://www.wikidata.org/wiki/Q7426587","display_name":"Saturation (graph theory)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2986422491","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing system","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2529999911785126},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec67600.2025.11196629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Due":[0],"to":[1,16,68],"the":[2,27,46,70,74],"growing":[3],"number":[4,75],"of":[5,20,30,76],"applications":[6],"utilizing":[7],"large":[8],"language":[9],"models,":[10],"understanding":[11],"hardware":[12],"requirements":[13],"becomes":[14],"imperative":[15],"ensure":[17],"efficient":[18],"operation":[19],"costly":[21],"computational":[22],"accelerators.":[23],"This":[24],"research":[25],"investigates":[26],"queuing":[28],"behavior":[29],"an":[31],"LLM":[32],"inference":[33],"server":[34],"as":[35,52],"it":[36],"operates":[37],"near":[38],"a":[39,53,57,62,79],"steady-state":[40],"regime.":[41],"It":[42],"is":[43,66],"shown":[44],"that":[45],"request":[47],"capacity":[48],"can":[49],"be":[50],"modeled":[51],"saturation":[54,71],"function":[55,65],"for":[56,73,78],"constant":[58],"arrival":[59,81],"rate.":[60,82],"Furthermore,":[61],"modified":[63],"exponential":[64],"demonstrated":[67],"predict":[69],"value":[72],"requests":[77],"given":[80]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-16T00:00:00"}
