{"id":"https://openalex.org/W7138896162","doi":"https://doi.org/10.1109/globecom59602.2025.11432267","title":"Latency-Aware LLM Deployment over Edge Networks","display_name":"Latency-Aware LLM Deployment over Edge Networks","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7138896162","doi":"https://doi.org/10.1109/globecom59602.2025.11432267"},"language":null,"primary_location":{"id":"doi:10.1109/globecom59602.2025.11432267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom59602.2025.11432267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","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/A5129983039","display_name":"Benedetta Picano","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Benedetta Picano","raw_affiliation_strings":["University of Florence,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florence,Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130015346","display_name":"Dinh Thai Hoang","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dinh Thai Hoang","raw_affiliation_strings":["University of Technology,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology,Sydney,Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111229171","display_name":"Diep N. Nguyen","orcid":"https://orcid.org/0000-0003-2659-8648"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Diep N. Nguyen","raw_affiliation_strings":["University of Technology,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology,Sydney,Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2481","last_page":"2486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2515000104904175,"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":0.2515000104904175,"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":0.1266999989748001,"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/T13918","display_name":"Advanced Data and IoT Technologies","score":0.08730000257492065,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.6675000190734863},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6571999788284302},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5717999935150146},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5590999722480774},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5246000289916992},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.48410001397132874},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4742000102996826},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43700000643730164},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990000247955322},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6675000190734863},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6571999788284302},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6380000114440918},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5717999935150146},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5246000289916992},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.46149998903274536},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.4059000015258789},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3630000054836273},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C61455927","wikidata":"https://www.wikidata.org/wiki/Q1030529","display_name":"Blossom algorithm","level":3,"score":0.33149999380111694},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C2777632111","wikidata":"https://www.wikidata.org/wiki/Q1937518","display_name":"Reservation","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.28060001134872437},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C2776061582","wikidata":"https://www.wikidata.org/wiki/Q25325231","display_name":"Mobile edge computing","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom59602.2025.11432267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom59602.2025.11432267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","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":23,"referenced_works":["https://openalex.org/W1815575988","https://openalex.org/W2126137945","https://openalex.org/W2588613254","https://openalex.org/W4389104713","https://openalex.org/W4390659326","https://openalex.org/W4391952557","https://openalex.org/W4391974543","https://openalex.org/W4392909588","https://openalex.org/W4399526294","https://openalex.org/W4400188118","https://openalex.org/W4400878080","https://openalex.org/W4401628481","https://openalex.org/W4402509398","https://openalex.org/W4402916969","https://openalex.org/W4403635975","https://openalex.org/W4404238218","https://openalex.org/W4404739647","https://openalex.org/W4404782827","https://openalex.org/W4405934565","https://openalex.org/W4409076673","https://openalex.org/W4414008559","https://openalex.org/W6922320873","https://openalex.org/W7124159067"],"related_works":[],"abstract_inverted_index":{"The":[0],"growing":[1],"size":[2],"and":[3,21,52,61,69,89],"complexity":[4],"of":[5],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"pose":[10],"major":[11],"challenges":[12],"for":[13,33,86,110],"deployment":[14],"in":[15,126],"edge":[16,39,112],"environments":[17],"with":[18,141],"limited":[19],"computational":[20],"communication":[22],"resources.":[23,113],"To":[24],"address":[25],"this,":[26],"we":[27,77],"propose":[28],"a":[29,46,80,123,142],"novel":[30],"distributed":[31],"framework":[32,101,140],"allocating":[34],"LLM":[35],"layers":[36,51],"across":[37],"heterogeneous":[38],"nodes.":[40],"By":[41],"modeling":[42],"the":[43,99,131,138],"problem":[44],"as":[45],"two-sided":[47],"matching":[48,82],"game,":[49],"where":[50,106],"nodes":[53],"rank":[54],"each":[55],"other":[56],"based":[57,145],"on":[58,146],"processing":[59],"delay":[60],"inter-node":[62],"transmission":[63],"latency,":[64],"our":[65,118],"approach":[66,119],"achieves":[67,120],"stable":[68],"low-latency":[70],"allocations":[71],"without":[72],"centralized":[73],"coordination.":[74],"In":[75],"particular,":[76],"first":[78],"design":[79],"lightweight":[81],"algorithm":[83],"that":[84,117],"accounts":[85],"pipeline":[87],"dependencies":[88],"mitigates":[90],"idle":[91],"periods":[92],"during":[93],"sequential":[94],"inference.":[95],"We":[96,135],"then":[97],"extend":[98],"proposed":[100,139],"to":[102,122,130],"support":[103],"multi-tenant":[104],"scenarios,":[105],"multiple":[107],"LLMs":[108],"compete":[109],"shared":[111],"Extensive":[114],"simulations":[115],"show":[116],"up":[121],"10%":[124],"reduction":[125],"inference":[127],"latency":[128],"compared":[129],"Kolkata":[132],"Game":[133],"baseline.":[134],"also":[136],"validate":[137],"real-world":[143],"testbed":[144],"LLaMA-7B":[147],"under":[148],"realistic":[149],"conditions.":[150]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-20T00:00:00"}
