{"id":"https://openalex.org/W7084026035","doi":"https://doi.org/10.1109/infocom55648.2025.11044734","title":"Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices","display_name":"Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W7084026035","doi":"https://doi.org/10.1109/infocom55648.2025.11044734"},"language":"en","primary_location":{"id":"doi:10.1109/infocom55648.2025.11044734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Shengyuan Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyuan Ye","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bei Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Ouyang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liekang Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liekang Zeng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianyi Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Qian","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaowen Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159029","display_name":"Guangzhou HKUST Fok Ying Tung Research Institute","ror":"https://ror.org/05cvbj479","country_code":"CN","type":"facility","lineage":["https://openalex.org/I200769079","https://openalex.org/I4210159029"]},{"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":["CN","HK"],"is_corresponding":false,"raw_author_name":"Xiaowen Chu","raw_affiliation_strings":["Data Science and Analytics Thrust, HKUST (Guangzhou),Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science and Analytics Thrust, HKUST (Guangzhou),Guangzhou,China","institution_ids":["https://openalex.org/I4210159029","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Tang","raw_affiliation_strings":["Midea Group,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Midea Group,China","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T13370","display_name":"Diverse Scientific and Economic Studies","score":0.08160000294446945,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13370","display_name":"Diverse Scientific and Economic Studies","score":0.08160000294446945,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14111","display_name":"Diverse Research Studies Overview","score":0.01360000018030405,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13398","display_name":"Data Analysis with R","score":0.013199999928474426,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/edge-computing","display_name":"Edge computing","score":0.6122999787330627},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5217999815940857},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5027999877929688},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.477400004863739},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4733000099658966},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.45680001378059387},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4415000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131999969482422},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.6122999787330627},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.529699981212616},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4352000057697296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.37630000710487366},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32589998841285706},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2581000030040741}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/infocom55648.2025.11044734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-162963","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-162963","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.599940299987793,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"have":[5],"garnered":[6],"significant":[7],"attention":[8],"due":[9],"to":[10,33,70,143,170,214],"their":[11],"exceptional":[12],"capabilities":[13],"in":[14,20,53],"various":[15,208],"AI":[16,122],"tasks.":[17],"Traditionally":[18],"deployed":[19],"cloud":[21],"datacenters,":[22],"LLMs":[23],"are":[24],"now":[25],"increasingly":[26],"moving":[27],"towards":[28],"more":[29],"accessible":[30],"edge":[31,48,68,89,121,209],"platforms":[32],"protect":[34],"sensitive":[35],"user":[36],"data":[37],"and":[38,58,86,118,137,150,163],"ensure":[39],"privacy":[40],"preservation.":[41],"The":[42],"limited":[43],"computational":[44],"resources":[45],"of":[46,75,88,147],"individual":[47,76],"devices,":[49,77],"however,":[50],"can":[51],"result":[52],"excessively":[54],"prolonged":[55],"in-ference":[56],"latency":[57,218],"overwhelmed":[59],"memory":[60],"usage.":[61],"While":[62],"existing":[63],"research":[64],"has":[65],"explored":[66],"collaborative":[67,120],"computing":[69],"break":[71],"the":[72,97,101,144,148],"resource":[73,172],"wall":[74],"these":[78],"solutions":[79],"yet":[80],"suffer":[81],"from":[82],"massive":[83],"communication":[84],"overhead":[85],"under-utilization":[87],"resources.":[90],"Furthermore,":[91],"they":[92],"focus":[93],"exclusively":[94],"on":[95,197],"optimizing":[96],"prefill":[98,149,154],"phase,":[99,155],"neglecting":[100],"crucial":[102],"autoregressive":[103],"decoding":[104,151,183],"phase":[105],"for":[106,124],"generative":[107,125],"LLMs.":[108],"To":[109],"address":[110],"that,":[111],"we":[112],"propose":[113],"Jupiter,":[114],"a":[115,130,135,158,165],"fast,":[116],"scalable,":[117],"resource-efficient":[119],"system":[123,140],"LLM":[126],"inference.":[127],"Jupiter":[128,156,176,202],"introduces":[129],"flexible":[131],"pipelined":[132],"architecture":[133],"as":[134],"principle":[136],"differentiates":[138],"its":[139],"design":[141],"according":[142],"differentiated":[145],"characteristics":[146],"phases.":[152],"For":[153,174],"submits":[157],"novel":[159],"intra-sequence":[160],"pipeline":[161,181],"parallelism":[162,167],"develops":[164],"meticulous":[166],"planning":[168],"strategy":[169],"maximize":[171],"efficiency;":[173],"decoding,":[175,188],"devises":[177],"an":[178],"effective":[179],"outline-based":[180],"parallel":[182],"mechanism":[184],"combined":[185],"with":[186],"speculative":[187],"which":[189],"further":[190],"magnifies":[191],"inference":[192],"acceleration.":[193],"Extensive":[194],"evaluation":[195],"based":[196],"realistic":[198],"implementation":[199],"demon-strates":[200],"that":[201],"remarkably":[203],"outperforms":[204],"state-of-the-art":[205],"approaches":[206],"under":[207],"environment":[210],"setups,":[211],"achieving":[212],"up":[213],"26.1":[215],"\u00d7":[216],"end-to-end":[217],"reduction":[219],"while":[220],"rendering":[221],"on-par":[222],"generation":[223],"quality.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}