{"id":"https://openalex.org/W4414197293","doi":"https://doi.org/10.1109/dac63849.2025.11132534","title":"LLMShare: Optimizing LLM Inference Serving with Hardware Architecture Exploration","display_name":"LLMShare: Optimizing LLM Inference Serving with Hardware Architecture Exploration","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414197293","doi":"https://doi.org/10.1109/dac63849.2025.11132534"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11132534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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/A5039526257","display_name":"Hongduo Liu","orcid":"https://orcid.org/0000-0001-7291-3712"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Hongduo Liu","raw_affiliation_strings":["CUHK"],"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662676","display_name":"Chen Bai","orcid":"https://orcid.org/0000-0002-1742-0090"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen Bai","raw_affiliation_strings":["HKUST"],"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001599037","display_name":"Peng Xu","orcid":"https://orcid.org/0000-0003-4268-4976"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peng Xu","raw_affiliation_strings":["CUHK"],"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114205035","display_name":"Lihao Yin","orcid":"https://orcid.org/0000-0002-8237-377X"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lihao Yin","raw_affiliation_strings":["Huawei Technologies"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102718069","display_name":"X. D. Yu","orcid":"https://orcid.org/0000-0002-6060-2383"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xianzhi Yu","raw_affiliation_strings":["Huawei Technologies"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031170152","display_name":"Hui\u2010Ling Zhen","orcid":"https://orcid.org/0000-0003-0310-3825"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hui-Ling Zhen","raw_affiliation_strings":["Huawei Technologies"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078949174","display_name":"Mingxuan Yuan","orcid":"https://orcid.org/0000-0002-2236-8784"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mingxuan Yuan","raw_affiliation_strings":["Huawei Technologies"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062800747","display_name":"Tsung-Yi Ho","orcid":"https://orcid.org/0000-0001-7348-5625"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tsung-Yi Ho","raw_affiliation_strings":["CUHK"],"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105870525","display_name":"Yu Bei","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bei Yu","raw_affiliation_strings":["CUHK"],"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5039526257"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":1.4196,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86254972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9617000222206116,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9617000222206116,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9394999742507935,"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/software-deployment","display_name":"Software deployment","score":0.6452999711036682},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.49630001187324524},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4884999990463257},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.461899995803833},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4584999978542328},{"id":"https://openalex.org/keywords/hardware-architecture","display_name":"Hardware architecture","score":0.4162999987602234},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4147000014781952},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.385699987411499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742999792098999},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6452999711036682},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4749999940395355},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.461899995803833},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4505999982357025},{"id":"https://openalex.org/C65232700","wikidata":"https://www.wikidata.org/wiki/Q5656403","display_name":"Hardware architecture","level":3,"score":0.4162999987602234},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3912000060081482},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.36010000109672546},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.34540000557899475},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.32420000433921814},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29660001397132874},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C31352089","wikidata":"https://www.wikidata.org/wiki/Q3750474","display_name":"Systems design","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11132534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2098907614","https://openalex.org/W2114188922","https://openalex.org/W2138209363","https://openalex.org/W2154327203","https://openalex.org/W2270330859","https://openalex.org/W2403021642","https://openalex.org/W3013899498","https://openalex.org/W3127736057","https://openalex.org/W4200520905","https://openalex.org/W4221000689","https://openalex.org/W4226441354","https://openalex.org/W4385245566","https://openalex.org/W4387321091","https://openalex.org/W4401211642","https://openalex.org/W4401211704","https://openalex.org/W4407217670","https://openalex.org/W4409306177"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"revolutionized":[5],"language":[6],"tasks":[7],"but":[8],"pose":[9],"significant":[10],"deployment":[11],"challenges":[12],"due":[13],"to":[14,49,91,123],"their":[15],"substantial":[16],"computational":[17,35],"demands":[18,103],"during":[19],"inference.":[20],"The":[21],"hardware":[22,63,81,98],"configurations":[23,64],"of":[24,39,104],"existing":[25],"LLM":[26,46,66],"serving":[27,125],"systems":[28],"do":[29],"not":[30],"optimize":[31],"for":[32,65],"the":[33,40,75,101,105],"different":[34,80],"and":[36,42,53,77,83,107,116],"bandwidth":[37],"needs":[38],"prefill":[41,106],"decoding":[43,108],"phases":[44],"in":[45],"inference,":[47],"leading":[48],"inefficient":[50],"resource":[51],"use":[52],"increased":[54],"costs.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,110],"systematically":[60],"investigate":[61],"promising":[62],"inference":[67],"serving.":[68],"We":[69],"develop":[70],"a":[71,85],"simulator":[72],"that":[73],"models":[74],"performance":[76],"cost":[78,114],"across":[79],"solutions":[82],"introduce":[84],"customized":[86],"design":[87],"space":[88],"exploration":[89],"framework":[90],"identify":[92],"optimal":[93],"setups":[94],"efficiently.":[95],"By":[96],"aligning":[97],"capabilities":[99],"with":[100],"specific":[102],"phases,":[109],"achieve":[111],"$13":[112],"\\%$":[113],"savings":[115],"over":[117],"$4":[118],"\\times$":[119],"throughput":[120],"improvements":[121],"compared":[122],"conventional":[124],"system":[126],"setups.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
