{"id":"https://openalex.org/W7155545501","doi":"https://doi.org/10.1145/3767295.3769315","title":"AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding","display_name":"AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7155545501","doi":"https://doi.org/10.1145/3767295.3769315"},"language":null,"primary_location":{"id":"doi:10.1145/3767295.3769315","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769315","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767295.3769315","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081700233","display_name":"Zikun Li","orcid":"https://orcid.org/0000-0001-6746-6225"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zikun Li","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6746-6225","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121287998","display_name":"Zhuofu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuofu Chen","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0009-0004-1735-4443","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134541538","display_name":"Remi Delacourt","orcid":"https://orcid.org/0009-0008-1319-4832"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Remi Delacourt","raw_affiliation_strings":["EPFL, Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0009-0008-1319-4832","affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073183750","display_name":"Gabriele Oliaro","orcid":"https://orcid.org/0000-0001-5406-0736"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriele Oliaro","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5406-0736","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006081199","display_name":"Zeyu Wang","orcid":"https://orcid.org/0009-0002-5756-2744"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Wang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0009-0002-5756-2744","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102629582","display_name":"Qinghan Chen","orcid":"https://orcid.org/0009-0001-2714-7438"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qinghan Chen","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0009-0001-4306-3998","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113103189","display_name":"S.-J. LIN","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhuai Lin","raw_affiliation_strings":["Carnegie Mellon University, Sunnyvale, CA, USA"],"raw_orcid":"https://orcid.org/0009-0005-7574-755X","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134503837","display_name":"April Yang","orcid":"https://orcid.org/0009-0004-4226-6509"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"April Yang","raw_affiliation_strings":["Carnegie Mellon University, Sunnyvale, CA, USA"],"raw_orcid":"https://orcid.org/0009-0004-4226-6509","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072348433","display_name":"Zhihao Zhang","orcid":"https://orcid.org/0009-0002-8409-2717"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihao Zhang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0009-0002-8409-2717","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018889907","display_name":"Zhuoming Chen","orcid":"https://orcid.org/0009-0006-7797-573X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoming Chen","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0009-0006-7797-573X","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010225004","display_name":"Y.-P. Lai","orcid":"https://orcid.org/0000-0002-2358-805X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi-Hsiang Lai","raw_affiliation_strings":["Amazon Web Services, San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2358-805X","affiliations":[{"raw_affiliation_string":"Amazon Web Services, San Jose, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040267796","display_name":"Xinhao Cheng","orcid":"https://orcid.org/0009-0009-3375-497X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinhao Cheng","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0009-0008-3981-9159","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015552951","display_name":"Xupeng Miao","orcid":"https://orcid.org/0000-0002-9371-8358"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xupeng Miao","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-9371-8358","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062437461","display_name":"Zhihao Jia","orcid":"https://orcid.org/0000-0002-1270-5185"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihao Jia","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1270-5185","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5081700233"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.948528,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.23659999668598175,"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/T10028","display_name":"Topic Modeling","score":0.23659999668598175,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2272000014781952,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03819999843835831,"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/decoding-methods","display_name":"Decoding methods","score":0.38960000872612},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2768000066280365},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2678000032901764},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.2540999948978424},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.22930000722408295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6033999919891357},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.22930000722408295},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2282000035047531},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2248000055551529},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.22200000286102295}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767295.3769315","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769315","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3767295.3769315","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769315","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4053463217","display_name":null,"funder_award_id":"CNS-2239351","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4786468689","display_name":null,"funder_award_id":"CNS-2211882","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2272351350","https://openalex.org/W4311887664"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"large":[1],"language":[2],"model":[3],"(LLM)":[4],"applications":[5],"exhibit":[6],"diverse":[7,118],"service-level":[8],"objectives":[9],"(SLOs),":[10],"from":[11],"low-latency":[12],"requirements":[13],"in":[14,22,145],"interactive":[15],"coding":[16],"assistants":[17],"to":[18,40,55,84,108,128,135,138],"more":[19],"relaxed":[20],"constraints":[21],"data":[23],"wrangling":[24],"tasks.":[25],"Existing":[26],"LLM":[27,51],"serving":[28,52,59,67],"systems,":[29],"which":[30],"rely":[31],"on":[32],"uniform":[33],"batching":[34],"and":[35,73,130],"scheduling":[36],"strategies,":[37],"often":[38],"fail":[39],"meet":[41],"these":[42],"heterogeneous":[43],"SLOs":[44],"concurrently.":[45],"We":[46],"present":[47],"AdaServe,":[48],"the":[49,139],"first":[50],"system":[53,103],"designed":[54],"support":[56],"efficient":[57],"multi-SLO":[58,66,146],"through":[60],"SLO-customized":[61],"speculative":[62],"decoding.":[63],"AdaServe":[64,105,122],"formulates":[65],"as":[68],"a":[69,75,80,91],"constrained":[70],"optimization":[71],"problem":[72],"introduces":[74],"hardware-aware":[76],"algorithm":[77],"that":[78,94,121],"constructs":[79],"speculation":[81,114],"tree":[82],"tailored":[83],"each":[85],"request's":[86],"latency":[87],"target.":[88],"It":[89],"features":[90],"speculate-select-verify":[92],"pipeline":[93],"enables":[95],"fine-grained":[96],"control":[97],"over":[98],"decoding":[99],"speed":[100],"while":[101],"maximizing":[102],"throughput.":[104],"further":[106],"adapts":[107],"workload":[109],"variation":[110],"by":[111,126,133],"dynamically":[112],"adjusting":[113],"parameters.":[115],"Evaluations":[116],"across":[117],"workloads":[119],"show":[120],"reduces":[123],"SLO":[124],"violations":[125],"up":[127,134],"4.3X":[129],"improves":[131],"goodput":[132],"1.9X":[136],"compared":[137],"best-performing":[140],"baselines,":[141],"highlighting":[142],"its":[143],"effectiveness":[144],"serving.":[147]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2026-04-25T00:00:00"}
