{"id":"https://openalex.org/W4414909322","doi":"https://doi.org/10.1109/cluster59342.2025.11186463","title":"Rock: Serving Multimodal Models in Cloud with Heterogeneous-Aware Resource Orchestration for Thousands of LoRA Adapters","display_name":"Rock: Serving Multimodal Models in Cloud with Heterogeneous-Aware Resource Orchestration for Thousands of LoRA Adapters","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4414909322","doi":"https://doi.org/10.1109/cluster59342.2025.11186463"},"language":"en","primary_location":{"id":"doi:10.1109/cluster59342.2025.11186463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster59342.2025.11186463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5040227806","display_name":"Shuaipeng Wu","orcid":"https://orcid.org/0009-0002-4764-2601"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuaipeng Wu","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033311175","display_name":"Yanying Lin","orcid":"https://orcid.org/0000-0002-4809-9543"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanying Lin","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102014822","display_name":"Shijie Peng","orcid":"https://orcid.org/0009-0005-1776-4773"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Peng","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101511923","display_name":"Wenyan Chen","orcid":"https://orcid.org/0000-0002-4821-9306"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyan Chen","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055979923","display_name":"Chong Ma","orcid":"https://orcid.org/0000-0002-5423-4449"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chong Ma","raw_affiliation_strings":["Alibaba Group Inc,AIOS Team"],"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc,AIOS Team","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109653794","display_name":"Min Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Shen","raw_affiliation_strings":["Alibaba Group Inc,AIOS Team"],"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc,AIOS Team","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420742","display_name":"Le Chen","orcid":"https://orcid.org/0000-0001-6019-0190"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le Chen","raw_affiliation_strings":["Alibaba Group Inc,AIOS Team"],"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc,AIOS Team","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100569901","display_name":"Chengzhong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chengzhong Xu","raw_affiliation_strings":["University of Macau"],"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086228898","display_name":"Kejiang Ye","orcid":"https://orcid.org/0000-0001-8985-2792"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejiang Ye","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5040227806"],"corresponding_institution_ids":["https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34155259,"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":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9797000288963318,"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"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9797000288963318,"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"}},{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9715999960899353,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9592999815940857,"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/adapter","display_name":"Adapter (computing)","score":0.7226999998092651},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.6899999976158142},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6890000104904175},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.6323999762535095},{"id":"https://openalex.org/keywords/burstiness","display_name":"Burstiness","score":0.4611000120639801},{"id":"https://openalex.org/keywords/cloudlet","display_name":"Cloudlet","score":0.4359999895095825},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39259999990463257},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.383899986743927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8361999988555908},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7226999998092651},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.6899999976158142},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6890000104904175},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6323999762535095},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5127000212669373},{"id":"https://openalex.org/C2781023610","wikidata":"https://www.wikidata.org/wiki/Q17006304","display_name":"Burstiness","level":3,"score":0.4611000120639801},{"id":"https://openalex.org/C2781055072","wikidata":"https://www.wikidata.org/wiki/Q25325266","display_name":"Cloudlet","level":3,"score":0.4359999895095825},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4059999883174896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.30889999866485596},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster59342.2025.11186463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster59342.2025.11186463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7672641152","display_name":null,"funder_award_id":"92267105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,28],"present":[4],"ROCK,":[5],"a":[6,79,106,120],"novel":[7],"system":[8,89],"for":[9,16,143],"efficiently":[10],"serving":[11],"thousands":[12],"of":[13,25,60],"LoRA":[14,144],"adapters":[15],"multimodal":[17],"models":[18],"in":[19,32],"cloud":[20],"environments.":[21],"Through":[22],"extensive":[23],"analysis":[24],"production":[26],"workloads,":[27],"identify":[29],"key":[30],"challenges":[31,77],"current":[33],"cloud-based":[34],"image":[35],"generation":[36],"services:":[37],"extreme":[38],"request":[39],"burstiness":[40],"(up":[41],"to":[42,97,155],"<tex":[43,67,131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[44,68,132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$90":[45],"\\times$</tex>":[46],"normal":[47],"rates),":[48],"heterogeneous":[49,92,116],"task":[50],"characteristics,":[51],"and":[52,63,86,105,135],"inefficient":[53],"adapter":[54,113,150],"management":[55],"that":[56,82,94,110,124],"wastes":[57],"40":[58],"%":[59,139],"GPU":[61],"memory":[62],"increases":[64],"delays":[65],"by":[66,130,153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$3":[69],"x$</tex>":[70],"during":[71],"peak":[72],"times.":[73],"ROCK":[74,125],"addresses":[75],"these":[76],"through":[78],"three-layer":[80],"architecture":[81],"decouples":[83],"hardware,":[84],"adapters,":[85],"requests.":[87],"Our":[88],"features":[90],"dynamic":[91],"queues":[93],"match":[95],"tasks":[96],"appropriate":[98],"resources":[99],"based":[100],"on":[101,119],"multidimensional":[102],"feature":[103],"vectors,":[104],"multilevel":[107],"orchestration":[108],"framework":[109],"intelligently":[111],"manages":[112],"placement":[114],"across":[115],"storage.":[117],"Experiments":[118],"64-GPU":[121],"testbed":[122],"demonstrate":[123],"reduces":[126],"average":[127],"response":[128],"latency":[129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$16-26":[133],"\\%$</tex>,":[134],"achieves":[136],"an":[137],"84.1":[138],"cache":[140],"hit":[141],"rate":[142],"adapters-outperforming":[145],"traditional":[146],"approaches":[147],"while":[148],"reducing":[149],"update":[151],"frequency":[152],"up":[154],"77":[156],"%.":[157]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
