{"id":"https://openalex.org/W7171393655","doi":"https://doi.org/10.1016/j.comnet.2026.112609","title":"Profit-aware deployment of large language model-enabled inference chains in data centers","display_name":"Profit-aware deployment of large language model-enabled inference chains in data centers","publication_year":2026,"publication_date":"2026-07-27","ids":{"openalex":"https://openalex.org/W7171393655","doi":"https://doi.org/10.1016/j.comnet.2026.112609"},"language":"en","primary_location":{"id":"doi:10.1016/j.comnet.2026.112609","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.comnet.2026.112609","pdf_url":null,"source":{"id":"https://openalex.org/S63392143","display_name":"Computer Networks","issn_l":"1389-1286","issn":["1389-1286","1872-7069"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.comnet.2026.112609","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100340307","display_name":"Yuqi Zhang","orcid":"https://orcid.org/0000-0002-3426-4544"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Zhang","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, China"],"raw_orcid":"https://orcid.org/0009-0003-1426-8673","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143711819","display_name":"Haochen Lv","orcid":"https://orcid.org/0009-0003-7009-4209"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haochen Lv","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, China"],"raw_orcid":"https://orcid.org/0009-0003-7009-4209","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079356223","display_name":"Danyang Zheng","orcid":"https://orcid.org/0000-0002-3031-7856"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Danyang Zheng","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, China"],"raw_orcid":"https://orcid.org/0000-0002-3031-7856","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055469395","display_name":"Chen Yang","orcid":"https://orcid.org/0000-0002-9296-0142"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yang","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143721367","display_name":"Huanlai Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanlai Xing","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069042354","display_name":"Xiaojun Cao","orcid":"https://orcid.org/0000-0001-5670-8196"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaojun Cao","raw_affiliation_strings":["Department of Computer Science, Georgia State University, USA"],"raw_orcid":"https://orcid.org/0000-0001-5670-8196","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia State University, USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143679410","display_name":"Jie Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Xu","raw_affiliation_strings":["School of Computer Science, University of Leeds, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Leeds, UK","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5143742012","display_name":"Fei Teng","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Teng","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, China","institution_ids":["https://openalex.org/I4800084"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079356223"],"corresponding_institution_ids":["https://openalex.org/I4800084"],"apc_list":{"value":2370,"currency":"USD","value_usd":2370},"apc_paid":{"value":2370,"currency":"USD","value_usd":2370},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88272815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"288","issue":null,"first_page":"112609","last_page":"112609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.3711000084877014,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.3711000084877014,"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/T12127","display_name":"Software System Performance and Reliability","score":0.10620000213384628,"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/T14347","display_name":"Big Data and Digital Economy","score":0.06530000269412994,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.729200005531311},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6521999835968018},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.29660001397132874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.911300003528595},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.729200005531311},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6521999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38769999146461487},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3278000056743622},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2531999945640564},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.comnet.2026.112609","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.comnet.2026.112609","pdf_url":null,"source":{"id":"https://openalex.org/S63392143","display_name":"Computer Networks","issn_l":"1389-1286","issn":["1389-1286","1872-7069"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Networks","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.comnet.2026.112609","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.comnet.2026.112609","pdf_url":null,"source":{"id":"https://openalex.org/S63392143","display_name":"Computer Networks","issn_l":"1389-1286","issn":["1389-1286","1872-7069"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Networks","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2440421249","display_name":null,"funder_award_id":"2682025GH021","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2915584714","display_name":null,"funder_award_id":"62302404","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6159829169","display_name":null,"funder_award_id":"2682026ZT007","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W3042732884","https://openalex.org/W3170672970","https://openalex.org/W3204493036","https://openalex.org/W3209697490","https://openalex.org/W4210301203","https://openalex.org/W4387321091","https://openalex.org/W4388208052","https://openalex.org/W4390771941","https://openalex.org/W4401386967","https://openalex.org/W4401386998","https://openalex.org/W4401717638","https://openalex.org/W4402692877","https://openalex.org/W4403278672","https://openalex.org/W4403320241","https://openalex.org/W4404789869","https://openalex.org/W4405785427","https://openalex.org/W4405787555","https://openalex.org/W4405934565","https://openalex.org/W4409494152","https://openalex.org/W4411403346","https://openalex.org/W4411446528","https://openalex.org/W4415284287","https://openalex.org/W4415689913","https://openalex.org/W4415828349","https://openalex.org/W4417052216","https://openalex.org/W4417282938","https://openalex.org/W4417526447"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"model":[2],"(LLM)":[3],"services":[4],"increasingly":[5],"rely":[6],"on":[7,50,60],"distributed":[8],"inference":[9,36,69,107],"across":[10],"multiple":[11],"GPU":[12],"servers":[13],"to":[14],"sustain":[15],"concurrent":[16],"requests":[17],"under":[18],"limited":[19],"compute,":[20],"memory,":[21],"and":[22,54,57,98,110,135,138,152,164,181,188],"bandwidth":[23],"resources.":[24],"In":[25],"such":[26],"settings,":[27],"a":[28,166],"partitioned":[29],"LLM":[30],"can":[31,93],"be":[32],"represented":[33],"as":[34],"an":[35,154],"chain":[37,70],"(InFC),":[38],"where":[39],"the":[40,45,51,55,61,67,83,145],"deployment":[41,71,105],"decision":[42],"determines":[43],"both":[44],"sustainable":[46],"concurrency":[47],"ceiling":[48],"(SCC)":[49],"revenue":[52],"side":[53],"memory":[56],"communication":[58],"overhead":[59],"cost":[62],"side.":[63],"This":[64],"paper":[65],"studies":[66],"profit-aware":[68,119],"(InFCD)":[72],"problem":[73],"in":[74],"heterogeneous":[75],"data":[76],"center":[77],"networks.":[78],"We":[79,142],"show":[80,172],"that":[81,173],"increasing":[82],"InFC":[84],"length":[85],"does":[86],"not":[87],"monotonically":[88],"improve":[89,99],"profit:":[90],"finer":[91],"partitioning":[92],"relieve":[94],"per-GPU":[95],"resource":[96],"bottlenecks":[97],"SCC,":[100,137],"but":[101],"may":[102],"also":[103],"increase":[104],"spread,":[106],"path":[108],"length,":[109],"internal":[111,132],"traffic.":[112],"To":[113],"capture":[114],"this":[115],"tradeoff,":[116],"we":[117],"formulate":[118],"InFCD":[120],"by":[121],"jointly":[122],"modeling":[123],"static-weight":[124],"vRAM":[125],"occupation,":[126,129],"per-user":[127],"KV-cache":[128],"user-side":[130],"traffic,":[131,134],"boundary":[133],"resource-coupled":[136],"prove":[139],"its":[140,161],"NP-hardness.":[141],"then":[143],"propose":[144],"Maximum":[146],"Sub-module":[147],"Deployment":[148],"Gain":[149],"(MSDG)":[150],"score":[151],"design":[153],"MSDG-based":[155],"greedy":[156],"algorithm.":[157],"Theoretical":[158],"analysis":[159],"characterizes":[160],"online":[162],"complexity":[163],"establishes":[165],"conditional":[167],"positive-profit":[168],"preservation":[169],"property.":[170],"Simulations":[171],"MSDG":[174],"improves":[175],"total":[176],"profit":[177],"over":[178],"SCC-oriented,":[179],"cost-oriented,":[180],"local-profit-oriented":[182],"baselines,":[183],"characterize":[184],"empirical":[185],"optimality":[186],"gaps":[187],"SLO":[189],"sensitivity.":[190]},"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2026-07-28T00:00:00"}
