{"id":"https://openalex.org/W4414170725","doi":"https://doi.org/10.1109/iwqos65803.2025.11143464","title":"Birds in Cages: Edge Inference Allocation for Distributed LLM Deployment","display_name":"Birds in Cages: Edge Inference Allocation for Distributed LLM Deployment","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4414170725","doi":"https://doi.org/10.1109/iwqos65803.2025.11143464"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos65803.2025.11143464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","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":"https://openalex.org/A5048316032","display_name":"Jiahao Zhu","orcid":"https://orcid.org/0009-0003-1442-7603"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Zhu","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035586306","display_name":"Lu Zhao","orcid":"https://orcid.org/0000-0002-7681-4372"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhao","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076605929","display_name":"Fu Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Xiao","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007119869","display_name":"Lingjie Duan","orcid":"https://orcid.org/0000-0002-0217-6507"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lingjie Duan","raw_affiliation_strings":["Singapore University of Technology and Design,Engineering Systems and Design Pillar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design,Engineering Systems and Design Pillar","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9814,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85985439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9968000054359436,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9968000054359436,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9926000237464905,"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/server","display_name":"Server","score":0.7876999974250793},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6772000193595886},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6668000221252441},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5927000045776367},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5444999933242798},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.5083000063896179},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.4918000102043152},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4880000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796500027179718},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.7876999974250793},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6772000193595886},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6668000221252441},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6316999793052673},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5927000045776367},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5444999933242798},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.4918000102043152},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4880000054836273},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35280001163482666},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C198370458","wikidata":"https://www.wikidata.org/wiki/Q586459","display_name":"Type inference","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos65803.2025.11143464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1490480374","display_name":null,"funder_award_id":"BK20243053,BK20230351,62402233,62427809,62472232,U24A20248,2024YFB2906704","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1542978866","display_name":null,"funder_award_id":"62125203","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G7179437801","display_name":null,"funder_award_id":"BG2024028","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2948371065","https://openalex.org/W4285257856","https://openalex.org/W4292779060","https://openalex.org/W4328007645","https://openalex.org/W4376167141","https://openalex.org/W4384918448","https://openalex.org/W4385570483","https://openalex.org/W4390816650","https://openalex.org/W4392207935","https://openalex.org/W4399121685","https://openalex.org/W4399665655","https://openalex.org/W4404562740"],"related_works":[],"abstract_inverted_index":{"The":[0],"distributed":[1,63,127,145],"deployment":[2,129],"of":[3,82,166,207],"Large":[4],"Language":[5],"Models":[6],"(LLM)":[7],"on":[8,35,161,200],"edge":[9,37,51,67,122,141],"servers":[10,68,142],"close":[11],"to":[12,20,46,49,69,119,143,192],"users":[13],"has":[14],"unlocked":[15],"the":[16,43,62,79,91,102,109,116,121,151,164,168,174,205],"service":[17,44,98,170],"provider's":[18],"potential":[19],"deliver":[21],"low-latency":[22],"inference.":[23],"To":[24],"obtain":[25],"more":[26,30],"benefit":[27],"by":[28,154],"serving":[29],"resource-demanding":[31],"inference":[32,48,65,123,175],"tasks":[33],"based":[34,199],"resource-limited":[36],"servers,":[38],"it":[39],"is":[40,185,190],"critical":[41],"for":[42,126,140],"provider":[45],"allocate":[47],"suitable":[50],"servers.":[52],"Three":[53],"new":[54],"challenges":[55],"hinder":[56],"existing":[57],"approaches":[58],"from":[59,76],"being":[60],"implemented:":[61],"LLM":[64,83,128,146],"requires":[66],"collaborate":[70],"following":[71],"a":[72,137,179,201],"novel":[73],"workflow":[74,139],"different":[75],"other":[77],"tasks;":[78],"generative":[80],"nature":[81],"incurs":[84],"uncertainty":[85],"in":[86,93],"task":[87],"resource":[88,152],"occupations;":[89],"considering":[90],"heterogeneity":[92],"users'":[94],"latency":[95,105],"requirements":[96],"and":[97],"benefit,":[99,171],"merely":[100],"minimizing":[101],"total":[103,169],"user-perceived":[104],"can":[106],"not":[107],"maximize":[108],"benefit.":[110],"In":[111],"this":[112],"paper,":[113],"we":[114,135,149,172],"make":[115],"first":[117],"attempt":[118],"study":[120],"allocation":[124,176],"problem":[125,177,183],"while":[130],"conquering":[131],"these":[132],"challenges.":[133],"Specifically,":[134],"propose":[136],"collaborative":[138],"conduct":[144],"inferences.":[147],"Then,":[148],"estimate":[150],"occupations":[153],"employing":[155],"Exact":[156],"Conic":[157],"Reformulation":[158],"(ECR).":[159],"Based":[160],"this,":[162],"with":[163],"objective":[165],"maximizing":[167],"formulate":[173],"as":[178],"binary":[180],"integer":[181],"programming":[182],"which":[184],"NP-hard.":[186],"An":[187],"approximate":[188,194],"algorithm":[189],"proposed":[191],"find":[193],"solutions":[195],"efficiently.":[196],"Extensive":[197],"experiments":[198],"real-world":[202],"dataset":[203],"demonstrate":[204],"performance":[206],"our":[208],"approach.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
