{"id":"https://openalex.org/W4414170782","doi":"https://doi.org/10.1109/iwqos65803.2025.11143449","title":"LLMConf: Knowledge-Enhanced Configuration Optimization for Large Language Model Inference","display_name":"LLMConf: Knowledge-Enhanced Configuration Optimization for Large Language Model Inference","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4414170782","doi":"https://doi.org/10.1109/iwqos65803.2025.11143449"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos65803.2025.11143449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143449","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/A5103245763","display_name":"Jincai He","orcid":"https://orcid.org/0000-0002-1211-6882"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingkai He","raw_affiliation_strings":["School of Systems Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Systems Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335066","display_name":"Pengfei Chen","orcid":"https://orcid.org/0000-0003-4891-4971"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694455","display_name":"Yilun Wang","orcid":"https://orcid.org/0000-0001-9416-2219"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilun Wang","raw_affiliation_strings":["School of Systems Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Systems Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073831644","display_name":"Haiyu Huang","orcid":"https://orcid.org/0009-0000-6146-2493"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyu Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111990976","display_name":"Chuanfu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanfu Zhang","raw_affiliation_strings":["School of Systems Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Systems Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113275902","display_name":"Haojia Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojia Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088230554","display_name":"Danwen Chen","orcid":"https://orcid.org/0000-0002-0716-4812"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danwen Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103245763"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12533359,"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":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9957000017166138,"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":0.9957000017166138,"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":0.9923999905586243,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/inference","display_name":"Inference","score":0.8093000054359436},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5278000235557556},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5067999958992004},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4032999873161316},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39100000262260437},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.34869998693466187},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.3377000093460083}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8093000054359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7944999933242798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5278000235557556},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5278000235557556},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43230000138282776},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3864000141620636},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.32919999957084656},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos65803.2025.11143449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143449","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":[{"id":"https://openalex.org/G2477268016","display_name":null,"funder_award_id":"2024YFB4505904","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7213717779","display_name":null,"funder_award_id":"62272495","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2022485595","https://openalex.org/W2085507535","https://openalex.org/W2085727995","https://openalex.org/W2884165914","https://openalex.org/W2948513753","https://openalex.org/W2962948349","https://openalex.org/W3047528232","https://openalex.org/W3145442896","https://openalex.org/W4281753793","https://openalex.org/W4292779060","https://openalex.org/W4320067888","https://openalex.org/W4380714904","https://openalex.org/W4385481791","https://openalex.org/W4387321091","https://openalex.org/W4389518997","https://openalex.org/W4392489911","https://openalex.org/W4403785764","https://openalex.org/W4403788992","https://openalex.org/W4403995666","https://openalex.org/W4405433119","https://openalex.org/W4409657546","https://openalex.org/W4412945623"],"related_works":[],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"are":[5],"widely":[6],"applied":[7],"across":[8,164,177],"various":[9],"domains,":[10],"improving":[11],"the":[12,64,69,81,94,99,148,153],"quality":[13],"of":[14,29,41,68,83,152,162],"LLM":[15,30,36,57,70,91,100,154,185],"inference":[16,31,37,58,71,101,155],"services":[17],"is":[18],"essential.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,46],"find":[24],"that":[25,54,87,140,172],"optimizing":[26,132],"configuration":[27,66,84,150],"parameters":[28,67,85,96,151],"engines":[32],"can":[33],"significantly":[34,89,142],"improve":[35],"performance":[38,51,59,92,117,134,167],"in":[39],"terms":[40],"latency":[42],"and":[43,115,183],"throughput.":[44],"Therefore,":[45],"propose":[47],"LLMConf,":[48],"an":[49,159],"automated":[50,106],"tuning":[52],"system":[53],"optimizes":[55],"multiple":[56,133],"metrics":[60],"by":[61,98],"searching":[62],"for":[63,130],"optimal":[65,128],"engine.":[72,102],"We":[73,103],"first":[74],"introduce":[75],"a":[76,122],"knowledge-enhanced":[77],"approach":[78],"to":[79,109,126,147],"identify":[80],"set":[82],"(LLMConfigs)":[86],"most":[88],"impact":[90],"from":[93],"adjustable":[95],"provided":[97],"then":[104],"perform":[105],"data":[107],"collection":[108],"build":[110],"functional":[111],"relationships":[112],"between":[113],"LLMConfigs":[114,129],"each":[116],"metric.":[118],"Additionally,":[119],"LLMConf":[120,141,157,173],"employs":[121],"multi-objective":[123],"optimization":[124],"module":[125],"obtain":[127],"simultaneously":[131],"metrics.":[135,168],"The":[136],"experimental":[137],"results":[138],"show":[139],"outperforms":[143],"existing":[144],"methods.":[145],"Compared":[146],"default":[149],"engine,":[156],"achieves":[158],"average":[160],"improvement":[161],"20.1%":[163],"7":[165],"key":[166],"Moreover,":[169],"experiments":[170],"demonstrate":[171],"has":[174],"strong":[175],"transferability":[176],"diverse":[178],"datasets,":[179],"varying":[180],"concurrency":[181],"levels":[182],"different":[184],"base":[186],"models.":[187]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}