{"id":"https://openalex.org/W7154089110","doi":"https://doi.org/10.1109/tpds.2026.3683122","title":"Workload-Adapted Resource Allocation for LLM Distributed Serving in Serverless Clusters","display_name":"Workload-Adapted Resource Allocation for LLM Distributed Serving in Serverless Clusters","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154089110","doi":"https://doi.org/10.1109/tpds.2026.3683122"},"language":null,"primary_location":{"id":"doi:10.1109/tpds.2026.3683122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3683122","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-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/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, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4809-9543","affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","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, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-1776-4773","affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652703","display_name":"Yanbo Li","orcid":"https://orcid.org/0000-0002-7324-7712"},"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":"Yanbo Li","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-5551-2584","affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077516117","display_name":"Shutian Luo","orcid":"https://orcid.org/0000-0002-3064-5841"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shutian Luo","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3064-5841","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133515675","display_name":"Haiying Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiying Shen","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7548-6223","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133530264","display_name":"Kejiang Ye","orcid":null},"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, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6133-407X","affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122955994","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, Macau, China"],"raw_orcid":"https://orcid.org/0000-0001-9480-0356","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42481213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"6","first_page":"1442","last_page":"1457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.121799997985363,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.121799997985363,"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/T12203","display_name":"Mobile Agent-Based Network Management","score":0.09109999984502792,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.0892999991774559,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.6029999852180481},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.5067999958992004},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.3792000114917755},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.35530000925064087},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3377000093460083},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.3287999927997589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8370000123977661},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.6118000149726868},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.6029999852180481},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4661000072956085},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.265500009059906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2026.3683122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3683122","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5840464552","display_name":null,"funder_award_id":"2023B1515130002","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"increasingly":[3],"rely":[4],"on":[5],"pipeline":[6,24],"parallelism":[7],"for":[8,58,92],"distributed":[9,60],"inference,":[10],"but":[11],"existing":[12,145],"systems":[13,148],"face":[14],"critical":[15,73],"challenges":[16,111],"in":[17,47,62,119,153],"serverless":[18,48,63,105,146],"environments:":[19],"heterogeneous":[20],"request":[21],"distributions":[22],"across":[23],"stages":[25],"and":[26,42,95],"unpredictable":[27],"workload":[28],"patterns":[29],"requiring":[30],"rapid":[31,126],"elasticity.":[32],"Traditional":[33],"static":[34],"resource":[35,55,68],"allocation":[36,56,87],"fails":[37],"to":[38,141,144],"address":[39],"pipeline-specific":[40],"bottlenecks":[41],"cold":[43],"start":[44],"delays":[45],"inherent":[46],"architectures.":[49],"We":[50],"propose":[51],"QUART,":[52],"a":[53],"workload-adapted":[54],"system":[57,108],"LLM":[59],"serving":[61],"clusters.":[64],"QUART":[65,134],"introduces":[66],"pipeline-aware":[67],"management":[69],"through:":[70],"(1)":[71],"latency-aware":[72],"stage":[74],"identification":[75],"using":[76],"coefficient":[77],"of":[78],"variation":[79],"(CV)-based":[80],"burst":[81],"propagation":[82],"analysis,":[83],"(2)":[84],"dynamic":[85],"replica":[86],"with":[88,100,130],"proportional-integral-derivative":[89],"(PID)":[90],"control":[91],"congested":[93],"stages,":[94],"(3)":[96],"hierarchical":[97],"parameter":[98],"caching":[99],"copy-on-write":[101],"mechanisms":[102],"enabling":[103],"sub-second":[104],"scaling.":[106],"The":[107],"addresses":[109],"serverless-specific":[110],"through":[112],"cache-aware":[113],"scheduling":[114],"that":[115],"maintains":[116],"model":[117],"parameters":[118],"memory,":[120],"eliminating":[121],"disk":[122],"I/O":[123],"overhead":[124],"during":[125],"scaling":[127],"events.":[128],"Evaluation":[129],"real-world":[131],"workloads":[132],"shows":[133],"reduces":[135],"average":[136],"response":[137],"latency":[138],"by":[139],"up":[140],"87.1%":[142],"compared":[143],"inference":[147],"while":[149],"achieving":[150],"2.37x":[151],"improvement":[152],"goodput.":[154]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2026-04-14T00:00:00"}
