{"id":"https://openalex.org/W4409657546","doi":"https://doi.org/10.1145/3696410.3714930","title":"SCOOT: SLO-Oriented Performance Tuning for LLM Inference Engines","display_name":"SCOOT: SLO-Oriented Performance Tuning for LLM Inference Engines","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409657546","doi":"https://doi.org/10.1145/3696410.3714930"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714930","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714930","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714930","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714930","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016780746","display_name":"Ke Cheng","orcid":"https://orcid.org/0000-0003-0336-6916"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Cheng","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0336-6916","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376384","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0002-1095-9632"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Wang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1095-9632","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wen Hu","orcid":"https://orcid.org/0000-0002-4874-2260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Hu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4874-2260","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037917035","display_name":"Tiannuo Yang","orcid":"https://orcid.org/0000-0001-5465-9626"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiannuo Yang","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5465-9626","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368377","display_name":"Jianguo Li","orcid":"https://orcid.org/0000-0002-8645-0680"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianguo Li","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8645-0680","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100394022","display_name":"Sheng Zhang","orcid":"https://orcid.org/0000-0002-6581-6399"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6581-6399","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":24.6004,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9928561,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9861000180244446,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9840999841690063,"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/computer-science","display_name":"Computer science","score":0.7355169653892517},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5865668058395386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21963679790496826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355169653892517},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5865668058395386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21963679790496826}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696410.3714930","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714930","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714930","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714930","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714930","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714930","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409657546.pdf","grobid_xml":"https://content.openalex.org/works/W4409657546.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1533803232","https://openalex.org/W1983221302","https://openalex.org/W1994005439","https://openalex.org/W2126105956","https://openalex.org/W2151084831","https://openalex.org/W2330661976","https://openalex.org/W2570373436","https://openalex.org/W2605101405","https://openalex.org/W2783694856","https://openalex.org/W2898416733","https://openalex.org/W3017091196","https://openalex.org/W3022630129","https://openalex.org/W3035677605","https://openalex.org/W3044147426","https://openalex.org/W3094704314","https://openalex.org/W3121642476","https://openalex.org/W3174969457","https://openalex.org/W3188253575","https://openalex.org/W4213153339","https://openalex.org/W4231361681","https://openalex.org/W4281758439","https://openalex.org/W4285043533","https://openalex.org/W4310561894","https://openalex.org/W4317883989","https://openalex.org/W4321177657","https://openalex.org/W4382246105","https://openalex.org/W4384918448","https://openalex.org/W4385568101","https://openalex.org/W4386528681","https://openalex.org/W4386709568","https://openalex.org/W4387321091","https://openalex.org/W4387929784","https://openalex.org/W4388482083","https://openalex.org/W4389519153","https://openalex.org/W4389519819","https://openalex.org/W4391623948","https://openalex.org/W4392489911","https://openalex.org/W4395112660","https://openalex.org/W4400909627","https://openalex.org/W4405876081","https://openalex.org/W6849765749"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"are":[5,66],"gaining":[6],"increasing":[7],"popularity":[8],"across":[9],"a":[10,123],"wide":[11],"range":[12],"of":[13,18,38,50,63,89],"web":[14],"applications,":[15],"it":[16],"is":[17,174],"great":[19],"importance":[20],"to":[21,30,77,103,126,134,148,177],"optimize":[22,78],"service-level":[23],"objectives":[24,107],"(SLOs)":[25],"for":[26,80],"LLM":[27,51,82,179],"inference":[28,52,83,91,180],"services":[29,65],"enhance":[31],"user":[32],"satisfaction":[33],"and":[34,58,97,110,121,184],"improve":[35,55,139],"the":[36,48,59,87,90,115,131,140,145,150,169,193],"competitiveness":[37],"cloud":[39],"vendors.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,69],"observe":[45],"that":[46,156],"adjusting":[47],"parameters":[49,88],"engines":[53,181],"can":[54],"service":[56,84],"performance,":[57],"optimal":[60],"parameter":[61],"configurations":[62],"different":[64],"different.":[67],"Therefore,":[68],"propose":[70],"SCOOT,":[71],"an":[72],"automatic":[73],"performance":[74],"tuning":[75,86,132,141,151,161,170],"system":[76],"SLOs":[79],"each":[81],"by":[85],"engine.":[92],"SCOOT":[93,113,143,157,173,187],"jointly":[94],"exploits":[95],"single-objective":[96],"multiple-objective":[98],"Bayesian":[99],"optimization":[100,106,165],"(BO)":[101],"techniques":[102,162],"handle":[104],"various":[105,178],"via":[108],"exploration":[109],"exploitation.":[111],"Moreover,":[112,172],"prunes":[114],"search":[116],"space":[117],"with":[118],"known":[119],"constraints":[120,129],"adopts":[122],"random":[124],"forest":[125],"learn":[127],"hidden":[128],"during":[130],"process":[133],"mitigate":[135],"invalid":[136],"exploration.":[137],"To":[138],"efficiency,":[142],"utilizes":[144],"parallel":[146],"suggestion":[147],"accelerate":[149],"process.":[152],"Extensive":[153],"experiments":[154],"demonstrate":[155],"considerably":[158],"outperforms":[159],"existing":[160],"in":[163,192],"SLO":[164],"while":[166],"greatly":[167],"improving":[168],"efficiency.":[171],"universally":[175],"applicable":[176],"including":[182],"vLLM":[183],"TensorRT-LLM.":[185],"Currently,":[186],"has":[188],"already":[189],"been":[190],"implemented":[191],"production":[194],"environment":[195],"at":[196],"Ant":[197],"Group.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}