{"id":"https://openalex.org/W4417282938","doi":"https://doi.org/10.1109/pimrc62392.2025.11274878","title":"Think Fast, Infer Smart: A Hybrid Distributed LLMs Inference at the Wireless Edge","display_name":"Think Fast, Infer Smart: A Hybrid Distributed LLMs Inference at the Wireless Edge","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4417282938","doi":"https://doi.org/10.1109/pimrc62392.2025.11274878"},"language":null,"primary_location":{"id":"doi:10.1109/pimrc62392.2025.11274878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pimrc62392.2025.11274878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","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/A5048768303","display_name":"Abdullatif Albaseer","orcid":"https://orcid.org/0000-0002-6886-6500"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Abdullatif Albaseer","raw_affiliation_strings":["Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060837020","display_name":"Elmahdi Bentafat","orcid":"https://orcid.org/0000-0001-9801-5582"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Elmahdi Bentafat","raw_affiliation_strings":["Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032368084","display_name":"Moqbel Hamood","orcid":"https://orcid.org/0000-0001-8174-7525"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Moqbel Hamood","raw_affiliation_strings":["Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037234286","display_name":"Mohamed Abdallah","orcid":"https://orcid.org/0000-0002-3261-7588"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mohamed Abdallah","raw_affiliation_strings":["Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008695053","display_name":"Ala Al\u2010Fuqaha","orcid":"https://orcid.org/0000-0002-0903-1204"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ala Al-Fuqaha","raw_affiliation_strings":["Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001299811","display_name":"Mounir Hamdi","orcid":"https://orcid.org/0000-0002-9766-0085"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mounir Hamdi","raw_affiliation_strings":["Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamad Bin Khalifa University,Division of Information and Computing Technology, College of Science and Engineering,Doha,Qatar","institution_ids":["https://openalex.org/I4210144839"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144839"],"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":"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":0.25769999623298645,"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":0.25769999623298645,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.2565000057220459,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.09229999780654907,"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/inference","display_name":"Inference","score":0.7922999858856201},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7131999731063843},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.583299994468689},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5338000059127808},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.5113999843597412},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49559998512268066},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.48330000042915344},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.47350001335144043},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.38029998540878296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335999846458435},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7922999858856201},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7131999731063843},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5727999806404114},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.48330000042915344},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.47350001335144043},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.3677999973297119},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C2781041963","wikidata":"https://www.wikidata.org/wiki/Q18348618","display_name":"Computation offloading","level":4,"score":0.3305000066757202},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C3017813396","wikidata":"https://www.wikidata.org/wiki/Q17078173","display_name":"Resource constraints","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C200157131","wikidata":"https://www.wikidata.org/wiki/Q4854763","display_name":"Bandwidth allocation","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pimrc62392.2025.11274878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pimrc62392.2025.11274878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","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":10,"referenced_works":["https://openalex.org/W4390659326","https://openalex.org/W4393160423","https://openalex.org/W4400118952","https://openalex.org/W4400277194","https://openalex.org/W4400447774","https://openalex.org/W4401628481","https://openalex.org/W4401878796","https://openalex.org/W4402350363","https://openalex.org/W4405934565","https://openalex.org/W4414008559"],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"at":[5],"the":[6,15,24,39,46,91,95,121,162,175,181,194,199,203,211,216],"wireless":[7],"edge":[8,89,92,131,176,187],"is":[9],"a":[10,73,100,116,220],"promising":[11],"solution":[12],"to":[13,30,58,129,170,180],"meet":[14],"low-latency,":[16],"high-computation":[17],"demands":[18],"of":[19,45,111,202],"next-generation":[20],"AI":[21],"applications.":[22],"Although":[23],"existing":[25],"literature":[26],"has":[27],"introduced":[28],"approaches":[29],"enable":[31],"distributed":[32],"LLM":[33,48,112],"inference,":[34],"these":[35,69],"methods":[36],"largely":[37],"overlook":[38],"distinct":[40],"computational":[41,86],"and":[42,52,61,94,136,154,198,231],"communication":[43],"characteristics":[44],"two-phase":[47],"inference":[49,76,81,224],"process\u2014the":[50],"pre-fill":[51,122],"decode":[53,204],"phases.":[54],"This":[55],"oversight":[56],"leads":[57],"suboptimal":[59],"performance":[60],"limits":[62],"scalability":[63],"in":[64,223,228,234],"real-world":[65],"deployments.":[66],"To":[67],"address":[68],"issues,":[70],"we":[71,124],"propose":[72],"novel":[74],"collaborative":[75],"framework":[77,102,166,213],"that":[78,103,210],"strategically":[79],"minimizes":[80],"latency":[82,145,196],"by":[83,115,146],"optimally":[84],"distributing":[85],"loads":[87],"across":[88],"devices,":[90,188],"server,":[93,177],"cloud.":[96],"Our":[97],"approach":[98],"introduces":[99],"hybrid":[101],"combines":[104],"head-wise":[105],"parallel":[106,134],"processing":[107],"with":[108],"layer-wise":[109],"partitioning":[110],"models,":[113],"supported":[114],"dual-phase":[117],"optimization":[118],"strategy.":[119],"In":[120,161],"phase,":[123,164],"optimize":[125,142],"assigning":[126],"attention":[127],"heads":[128],"selected":[130],"devices":[132],"for":[133,143],"computation":[135],"efficient":[137],"resource":[138,235],"use.":[139],"We":[140],"then":[141],"minimal":[144],"selecting":[147],"participants,":[148],"determining":[149],"head":[150],"assignments":[151],"per":[152],"device,":[153],"allocating":[155],"bandwidth":[156,229],"while":[157],"meeting":[158],"all":[159],"constraints.":[160],"de-code":[163],"our":[165],"adaptively":[167],"decides":[168],"whether":[169],"execute":[171],"computations":[172],"locally":[173],"on":[174,193],"offload":[178],"them":[179],"cloud,":[182],"or":[183],"redistribute":[184],"tasks":[185],"among":[186],"optimizing":[189],"this":[190],"decision":[191],"based":[192],"remaining":[195],"budget":[197],"sequential":[200],"nature":[201],"phase.":[205],"The":[206],"simulation":[207],"results":[208],"demonstrate":[209],"proposed":[212],"significantly":[214],"outperforms":[215],"baseline":[217],"methods,":[218],"achieving":[219],"56%":[221],"reduction":[222],"latency,":[225],"40%":[226],"improvement":[227,233],"efficiency":[230],"35%":[232],"utilization.":[236]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-12T00:00:00"}
