{"id":"https://openalex.org/W4403534172","doi":"https://doi.org/10.1109/access.2024.3483250","title":"Enhancing LoRA Model Serving Capacity via Adaptive Operator Scheduling for Multi-Tenancy on GPU","display_name":"Enhancing LoRA Model Serving Capacity via Adaptive Operator Scheduling for Multi-Tenancy on GPU","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403534172","doi":"https://doi.org/10.1109/access.2024.3483250"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3483250","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3483250","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3483250","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052358046","display_name":"Lingnan Xia","orcid":"https://orcid.org/0000-0003-3525-5647"},"institutions":[{"id":"https://openalex.org/I4210152160","display_name":"Zhengzhou Railway Vocational & Technical College","ror":"https://ror.org/04zs83x19","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingnan Xia","raw_affiliation_strings":["Henan High-Speed Railway Operation and Maintenance Engineering Research Center, Zhengzhou Railway Vocational and Technical College, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3525-5647","affiliations":[{"raw_affiliation_string":"Henan High-Speed Railway Operation and Maintenance Engineering Research Center, Zhengzhou Railway Vocational and Technical College, Zhengzhou, China","institution_ids":["https://openalex.org/I4210152160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080510904","display_name":"Hua Ma","orcid":"https://orcid.org/0009-0003-7746-4639"},"institutions":[{"id":"https://openalex.org/I4210152160","display_name":"Zhengzhou Railway Vocational & Technical College","ror":"https://ror.org/04zs83x19","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Ma","raw_affiliation_strings":["Henan High-Speed Railway Operation and Maintenance Engineering Research Center, Zhengzhou Railway Vocational and Technical College, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-7746-4639","affiliations":[{"raw_affiliation_string":"Henan High-Speed Railway Operation and Maintenance Engineering Research Center, Zhengzhou Railway Vocational and Technical College, Zhengzhou, China","institution_ids":["https://openalex.org/I4210152160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210152160"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26262068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"160441","last_page":"160449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11325","display_name":"Inertial Sensor and Navigation","score":0.9280999898910522,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11325","display_name":"Inertial Sensor and Navigation","score":0.9280999898910522,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/computer-science","display_name":"Computer science","score":0.7198638916015625},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5815792679786682},{"id":"https://openalex.org/keywords/multitenancy","display_name":"Multitenancy","score":0.5194330215454102},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.47544145584106445},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.46778759360313416},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.457286536693573},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36847826838493347},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1889340877532959},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1638384461402893},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.15502125024795532},{"id":"https://openalex.org/keywords/software-as-a-service","display_name":"Software as a service","score":0.07665365934371948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7198638916015625},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5815792679786682},{"id":"https://openalex.org/C69016650","wikidata":"https://www.wikidata.org/wiki/Q1364211","display_name":"Multitenancy","level":5,"score":0.5194330215454102},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.47544145584106445},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.46778759360313416},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.457286536693573},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36847826838493347},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1889340877532959},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1638384461402893},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.15502125024795532},{"id":"https://openalex.org/C175133352","wikidata":"https://www.wikidata.org/wiki/Q1254596","display_name":"Software as a service","level":4,"score":0.07665365934371948},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3483250","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3483250","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1742ffcc3e51478c87658eb849086287","is_oa":true,"landing_page_url":"https://doaj.org/article/1742ffcc3e51478c87658eb849086287","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 160441-160449 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3483250","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3483250","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G3322344490","display_name":null,"funder_award_id":"242102241064","funder_id":"https://openalex.org/F4320336593","funder_display_name":"Henan Provincial Science and Technology Research Project"},{"id":"https://openalex.org/G5725460890","display_name":null,"funder_award_id":"232102240089","funder_id":"https://openalex.org/F4320336593","funder_display_name":"Henan Provincial Science and Technology Research Project"}],"funders":[{"id":"https://openalex.org/F4320336593","display_name":"Henan Provincial Science and Technology Research Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2096070062","https://openalex.org/W2100218206","https://openalex.org/W2471164860","https://openalex.org/W2810610794","https://openalex.org/W2951841630","https://openalex.org/W2961619211","https://openalex.org/W3008788679","https://openalex.org/W3012249773","https://openalex.org/W3096395190","https://openalex.org/W3136479147","https://openalex.org/W3204998121","https://openalex.org/W4251637954","https://openalex.org/W4287774892","https://openalex.org/W4299968636","https://openalex.org/W4321636575","https://openalex.org/W4384918448","https://openalex.org/W4387321091","https://openalex.org/W6751349269","https://openalex.org/W6752057402","https://openalex.org/W6752911319","https://openalex.org/W6769243733","https://openalex.org/W6779058226","https://openalex.org/W6779728309","https://openalex.org/W6779985863","https://openalex.org/W6838322825","https://openalex.org/W6847386241","https://openalex.org/W6850927664","https://openalex.org/W6854866820","https://openalex.org/W6857915566"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Low-Rank":[0],"Adaptation":[1],"(LoRA)":[2],"has":[3],"garnered":[4],"increasing":[5],"attention":[6],"for":[7,76],"effectively":[8],"fine-tuning":[9],"large":[10],"language":[11],"models":[12,25],"(LLMs)":[13],"with":[14],"limited":[15],"resources.":[16],"Nonetheless,":[17],"conventional":[18],"approaches":[19],"that":[20,143,159],"cater":[21],"to":[22,28,51,62,95,113,149,152,167],"multiple":[23],"LoRA":[24,78,173],"independently":[26],"lead":[27],"redundant":[29],"computations":[30],"and":[31,109,117],"suboptimal":[32],"GPU":[33,74],"utilization.":[34],"This":[35,138],"study":[36],"tackles":[37],"these":[38,126],"inefficiencies":[39],"by":[40,132,165],"presenting":[41],"Dynamic":[42],"Operator":[43],"Optimization,":[44],"a":[45,82,91,97,115,133],"sophisticated":[46],"automated":[47],"optimization":[48,140],"methodology":[49],"crafted":[50],"dynamically":[52,147],"enhance":[53],"the":[54,71,102],"Segmented":[55],"Gather":[56],"Matrix-Vector":[57],"Multiplication":[58],"(SGMV)":[59],"operator":[60,119],"according":[61],"specific":[63],"contexts.":[64],"The":[65,88,156],"distinctive":[66],"design":[67,161],"of":[68,73],"SGMV":[69,144],"facilitates":[70],"batching":[72],"operations":[75],"diverse":[77],"models,":[79],"resulting":[80],"in":[81,85,170],"notable":[83],"enhancement":[84],"computational":[86],"efficiency.":[87],"strategy":[89],"exploits":[90],"Search":[92],"Space":[93],"Constructor":[94],"construct":[96],"structured":[98],"search":[99,130],"space,":[100],"segmenting":[101],"program":[103],"space":[104],"into":[105],"overarching":[106],"structural":[107],"outlines":[108],"intricate":[110],"implementation":[111],"particulars":[112],"ensure":[114],"varied":[116],"adaptable":[118],"implementation.":[120],"Moreover,":[121],"an":[122],"Optimization":[123],"Engine":[124],"fine-tunes":[125],"implementations":[127,145],"through":[128],"evolutionary":[129],"driven":[131],"performance":[134],"estimation":[135],"cost":[136],"model.":[137],"progressive":[139],"procedure":[141],"ensures":[142],"can":[146,162],"adjust":[148],"varying":[150],"scenarios":[151],"uphold":[153],"superior":[154],"performance.":[155],"findings":[157],"illustrate":[158],"our":[160],"elevate":[163],"throughput":[164],"up":[166],"1.46":[168],"times":[169],"cutting-edge":[171],"multi-tenant":[172],"deployments.":[174]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}
