{"id":"https://openalex.org/W4409282468","doi":"https://doi.org/10.1145/3676536.3676659","title":"ALISE: Accelerating Large Language Model Serving with Speculative Scheduling","display_name":"ALISE: Accelerating Large Language Model Serving with Speculative Scheduling","publication_year":2024,"publication_date":"2024-10-27","ids":{"openalex":"https://openalex.org/W4409282468","doi":"https://doi.org/10.1145/3676536.3676659"},"language":"en","primary_location":{"id":"doi:10.1145/3676536.3676659","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676536.3676659","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676659","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676659","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054135724","display_name":"Youpeng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Youpeng Zhao","raw_affiliation_strings":["University of Central Florida, Orlando, United States"],"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, United States","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100384682","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-0926-4761"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["University of Central Florida, Orlando, USA"],"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054135724"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.7283,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7880142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9988999962806702,"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":0.9830999970436096,"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/computer-science","display_name":"Computer science","score":0.7667478322982788},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5980919003486633},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.4935101270675659},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4160591959953308},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1864200234413147},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07055366039276123},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.07023698091506958},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.0574202835559845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667478322982788},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5980919003486633},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.4935101270675659},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4160591959953308},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1864200234413147},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07055366039276123},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.07023698091506958},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0574202835559845}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676536.3676659","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676536.3676659","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676659","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3676536.3676659","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676536.3676659","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676659","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G7037565394","display_name":null,"funder_award_id":"2400014","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8237536803","display_name":null,"funder_award_id":"1907765","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409282468.pdf","grobid_xml":"https://content.openalex.org/works/W4409282468.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2734941459","https://openalex.org/W2933138175","https://openalex.org/W2954698171","https://openalex.org/W4249712447","https://openalex.org/W4281758439","https://openalex.org/W4387321091"],"related_works":["https://openalex.org/W1809394610","https://openalex.org/W2128410848","https://openalex.org/W2118368532","https://openalex.org/W2014085448","https://openalex.org/W2102390841","https://openalex.org/W3047653192","https://openalex.org/W2096289371","https://openalex.org/W2126232624","https://openalex.org/W2434525066","https://openalex.org/W3140149227"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"represent":[4],"a":[5],"revolutionary":[6],"advancement":[7],"in":[8],"the":[9,36,41],"contemporary":[10],"landscape":[11],"of":[12,38],"artificial":[13],"general":[14],"intelligence":[15],"(AGI).":[16],"As":[17],"exemplified":[18],"by":[19,47],"ChatGPT,":[20],"LLM-based":[21],"applications":[22],"necessitate":[23],"minimal":[24],"response":[25,61],"latency":[26],"and":[27,58],"maximal":[28],"throughput":[29],"for":[30],"inference":[31],"serving.":[32],"However,":[33],"due":[34],"to":[35],"unpredictability":[37],"LLM":[39,49],"execution,":[40],"first-come-first-serve":[42],"(FCFS)":[43],"scheduling":[44],"policy":[45],"employed":[46],"current":[48],"serving":[50],"systems":[51],"suffers":[52],"from":[53],"head-of-line":[54],"(HoL)":[55],"blocking":[56],"issues":[57],"long":[59],"job":[60],"times.":[62]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}
