{"id":"https://openalex.org/W4417258213","doi":"https://doi.org/10.1109/icmla66185.2025.00119","title":"EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model","display_name":"EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4417258213","doi":"https://doi.org/10.1109/icmla66185.2025.00119"},"language":"en","primary_location":{"id":"doi:10.1109/icmla66185.2025.00119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.09061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120777683","display_name":"Alyssa Pinnock","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alyssa Pinnock","raw_affiliation_strings":["University of Central Florida"],"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120777684","display_name":"Shakya Jayakody","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shakya Jayakody","raw_affiliation_strings":["University of Central Florida"],"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120777685","display_name":"Kawsher A Roxy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kawsher A Roxy","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058370129","display_name":"Moataz Ahmed","orcid":"https://orcid.org/0000-0003-0042-8819"},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Rubel Ahmed","raw_affiliation_strings":["Louisiana Tech University"],"affiliations":[{"raw_affiliation_string":"Louisiana Tech University","institution_ids":["https://openalex.org/I919208787"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120777683"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20709711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"814","last_page":"819"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3598000109195709,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3598000109195709,"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"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.20829999446868896,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.039500001817941666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.8443999886512756},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5720999836921692},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5633999705314636},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5270000100135803},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4968000054359436},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4507000148296356},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.42820000648498535}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8443999886512756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6442000269889832},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4507000148296356},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.42820000648498535},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.400299996137619},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C2987376176","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy inference system","level":5,"score":0.32089999318122864},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3118000030517578},{"id":"https://openalex.org/C2780331096","wikidata":"https://www.wikidata.org/wiki/Q24965464","display_name":"Energy modeling","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C146481406","wikidata":"https://www.wikidata.org/wiki/Q105131","display_name":"Hotspot (geology)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C2985973956","wikidata":"https://www.wikidata.org/wiki/Q1617745","display_name":"High energy","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icmla66185.2025.00119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.09061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.09061","pdf_url":"https://arxiv.org/pdf/2506.09061","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},{"id":"doi:10.48550/arxiv.2506.09061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.09061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.09061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.09061","pdf_url":"https://arxiv.org/pdf/2506.09061","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"EdgeProfiler,":[3],"a":[4,49,130],"fast":[5],"profiling":[6,91,161],"framework":[7,61],"designed":[8],"for":[9,52,136],"evaluating":[10],"lightweight":[11,164],"Large":[12],"Language":[13],"Models":[14],"(LLMs)":[15],"on":[16,142],"edge":[17,58,125,167],"systems.":[18],"While":[19],"LLMs":[20,165],"offer":[21],"remarkable":[22],"capabilities":[23],"in":[24,56,133,166],"natural":[25],"language":[26],"understanding":[27],"and":[28,34,69,75,87,149,173],"generation,":[29],"their":[30],"high":[31],"computational,":[32],"memory,":[33],"power":[35],"requirements":[36],"often":[37],"confine":[38],"them":[39],"to":[40,83,115,120,163],"cloud":[41],"environments.":[42],"EdgeProfiler":[43],"addresses":[44],"these":[45],"challenges":[46],"by":[47,100,117],"providing":[48],"systematic":[50],"methodology":[51],"assessing":[53],"LLM":[54],"performance":[55],"resource-constrained":[57],"settings.":[59],"The":[60,90],"profiles":[62],"compact":[63],"LLMs,":[64],"including":[65],"TinyLLaMA,":[66],"Gemma3-1B,":[67],"LLaMA3-1B,":[68],"DeepSeek-R1-1.5B,":[70],"using":[71],"aggressive":[72],"quantization":[73,95],"techniques":[74],"strict":[76],"memory":[77,98],"constraints.":[78],"Analytical":[79],"modeling":[80,128],"is":[81],"used":[82],"estimate":[84],"latency,":[85],"FLOPs,":[86],"energy":[88,134,171],"consumption.":[89],"reveals":[92],"that":[93],"4-bit":[94],"reduces":[96],"model":[97],"usage":[99],"approximately":[101],"60\u201370%,":[102],"while":[103],"maintaining":[104],"accuracy":[105],"within":[106],"2\u20135%":[107],"of":[108,159],"full-precision":[109],"baselines.":[110],"Inference":[111],"speeds":[112],"are":[113],"observed":[114],"improve":[116],"2\u20133\u00d7":[118],"compared":[119],"FP16":[121],"baselines":[122],"across":[123],"various":[124],"devices.":[126],"Power":[127],"estimates":[129],"35\u201350%":[131],"reduction":[132],"consumption":[135],"INT4":[137],"configurations,":[138],"enabling":[139],"practical":[140],"deployment":[141],"hardware":[143],"such":[144],"as":[145],"Raspberry":[146],"Pi":[147],"4/5":[148],"Jetson":[150],"Orin":[151],"Nano":[152],"Super.":[153],"Our":[154],"findings":[155],"emphasize":[156],"the":[157],"importance":[158],"efficient":[160],"tailored":[162],"environments,":[168],"balancing":[169],"accuracy,":[170],"efficiency,":[172],"computational":[174],"feasibility.":[175]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2025-10-10T00:00:00"}