{"id":"https://openalex.org/W4404386015","doi":"https://doi.org/10.1145/3698038.3698523","title":"Queue Management for SLO-Oriented Large Language Model Serving","display_name":"Queue Management for SLO-Oriented Large Language Model Serving","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404386015","doi":"https://doi.org/10.1145/3698038.3698523"},"language":null,"primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698038.3698523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5036886711","display_name":"Archit Patke","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Archit Patke","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058874649","display_name":"Dhemath Reddy","orcid":"https://orcid.org/0000-0002-9725-5952"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhemath Reddy","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016778130","display_name":"Saurabh Jha","orcid":"https://orcid.org/0000-0003-0926-0776"},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Jha","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037793114","display_name":"Haoran Qiu","orcid":"https://orcid.org/0000-0002-8071-1130"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoran Qiu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031211716","display_name":"Christian Pinto","orcid":"https://orcid.org/0000-0001-7060-2742"},"institutions":[{"id":"https://openalex.org/I4210145784","display_name":"IBM Research - Ireland","ror":"https://ror.org/04jnxr720","country_code":"IE","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145784"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Christian Pinto","raw_affiliation_strings":["IBM Research, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"IBM Research, Dublin, Ireland","institution_ids":["https://openalex.org/I4210145784"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043854372","display_name":"Chandra Narayanaswami","orcid":"https://orcid.org/0000-0002-4242-5352"},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandra Narayanaswami","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043860236","display_name":"Zbigniew Kalbarczyk","orcid":"https://orcid.org/0009-0002-6040-6865"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zbigniew Kalbarczyk","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067802693","display_name":"Ravishankar K. Iyer","orcid":"https://orcid.org/0000-0003-2245-3038"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravishankar Iyer","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":83},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"35"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9934,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9934,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13382","display_name":"Robotics and Automated Systems","score":0.9862,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9831,"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"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7636549},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.48901877},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.45549545}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698038.3698523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":16,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2560674852","https://openalex.org/W2734941459","https://openalex.org/W2926143647","https://openalex.org/W3026530461","https://openalex.org/W3087472809","https://openalex.org/W3095488153","https://openalex.org/W3130716829","https://openalex.org/W4281654814","https://openalex.org/W4321448364","https://openalex.org/W4322718191","https://openalex.org/W4387321091","https://openalex.org/W4392490478","https://openalex.org/W4394998727","https://openalex.org/W4395686786","https://openalex.org/W4399453677"],"related_works":["https://openalex.org/W4396701345","https://openalex.org/W4396696052","https://openalex.org/W4391913857","https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2001405890"],"abstract_inverted_index":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4404386015","counts_by_year":[],"updated_date":"2025-01-12T00:57:45.558009","created_date":"2024-11-15"}