{"id":"https://openalex.org/W4414169999","doi":"https://doi.org/10.1109/iwqos65803.2025.11143270","title":"JointSerLoRA: Cache-Aware LoRA Inference Serving","display_name":"JointSerLoRA: Cache-Aware LoRA Inference Serving","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4414169999","doi":"https://doi.org/10.1109/iwqos65803.2025.11143270"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos65803.2025.11143270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"},"type":"article","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/A5100448539","display_name":"Rui Li","orcid":"https://orcid.org/0000-0002-7669-4112"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Li","raw_affiliation_strings":["National University of Defense Technology,State Key Laboratory of Complex &#x0026; Critical Software Environment College of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,State Key Laboratory of Complex &#x0026; Critical Software Environment College of Computer Science and Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103148479","display_name":"Han Bao","orcid":"https://orcid.org/0000-0002-5617-2624"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Bao","raw_affiliation_strings":["National University of Defense Technology,State Key Laboratory of Complex &#x0026; Critical Software Environment College of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,State Key Laboratory of Complex &#x0026; Critical Software Environment College of Computer Science and Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076087924","display_name":"Huaimin Wang","orcid":"https://orcid.org/0000-0003-0376-640X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaimin Wang","raw_affiliation_strings":["National University of Defense Technology,State Key Laboratory of Complex &#x0026; Critical Software Environment College of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,State Key Laboratory of Complex &#x0026; Critical Software Environment College of Computer Science and Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023989290","display_name":"Peichang Shi","orcid":"https://orcid.org/0000-0002-0973-7899"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peichang Shi","raw_affiliation_strings":["National University of Defense Technology,State Key Laboratory of Complex &#x0026; Critical Software Environment College of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,State Key Laboratory of Complex &#x0026; Critical Software Environment College of Computer Science and Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027599015","display_name":"Grace Y. Yi","orcid":"https://orcid.org/0000-0002-0081-873X"},"institutions":[{"id":"https://openalex.org/I4210114190","display_name":"Shanghai Zhangjiang Laboratory","ror":"https://ror.org/0208qbg77","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodong Yi","raw_affiliation_strings":["Xiangjiang Lab"],"affiliations":[{"raw_affiliation_string":"Xiangjiang Lab","institution_ids":["https://openalex.org/I4210114190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100448539"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25405993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9958000183105469,"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"}},"topics":[{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9958000183105469,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9891999959945679,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/cache","display_name":"Cache","score":0.6531999707221985},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.567799985408783},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5171999931335449},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.48010000586509705},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.42500001192092896},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.37779998779296875},{"id":"https://openalex.org/keywords/systems-architecture","display_name":"Systems architecture","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8640999794006348},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6531999707221985},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.567799985408783},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46549999713897705},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.3569999933242798},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35499998927116394},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.3391000032424927},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos65803.2025.11143270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","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":1,"referenced_works":["https://openalex.org/W4387321091"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"enable":[4],"versatile":[5],"applications,":[6],"with":[7,84],"fine-tuning":[8],"methods":[9],"like":[10],"LoRA":[11,22,51],"optimizing":[12],"them":[13],"for":[14,20,65,87],"specific":[15],"domains.":[16],"However,":[17],"ensuring":[18],"QoS":[19],"dynamic":[21],"inference":[23,58],"on":[24],"heterogeneous":[25],"devices":[26],"is":[27],"challenging":[28],"due":[29],"to":[30,110],"memory":[31],"contention":[32],"from":[33],"the":[34,47],"shared":[35],"LLM":[36],"base":[37],"model":[38],"and":[39,50,76,79,89,102],"KV":[40,48,66],"cache.":[41],"Existing":[42],"solutions":[43],"lack":[44],"coordination":[45],"between":[46],"cache":[49,67],"scheduling.":[52],"We":[53],"propose":[54],"JointSerLoRA,":[55],"a":[56,62,70,81],"two-level":[57],"system":[59],"featuring:":[60],"(1)":[61],"disaggregated":[63],"architecture":[64],"consistency,":[68],"(2)":[69],"global":[71],"scheduler":[72,83],"balancing":[73],"adaptercache":[74],"reuse":[75],"GPU":[77],"load,":[78],"(3)":[80],"local":[82],"adaptive":[85],"batching":[86],"prefix":[88],"adapter-aware":[90],"grouping.":[91],"Evaluations":[92],"show":[93],"that":[94],"JointSerLoRA":[95],"reduces":[96],"end-to-end":[97],"latency":[98],"by":[99,104],"29":[100],"%":[101],"TTFT":[103],"<tex":[105],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[106],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$3.8":[107],"\\times$</tex>":[108],"compared":[109],"state-of-the-art":[111],"systems.":[112]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
