{"id":"https://openalex.org/W4408847395","doi":"https://doi.org/10.1145/3689031.3696086","title":"Stateful Large Language Model Serving with Pensieve","display_name":"Stateful Large Language Model Serving with Pensieve","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4408847395","doi":"https://doi.org/10.1145/3689031.3696086"},"language":"en","primary_location":{"id":"doi:10.1145/3689031.3696086","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689031.3696086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052479606","display_name":"Lingfan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingfan Yu","raw_affiliation_strings":["New York University"],"raw_orcid":"https://orcid.org/0009-0008-7711-263X","affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069998725","display_name":"Jinkun Lin","orcid":"https://orcid.org/0000-0003-0035-4266"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinkun Lin","raw_affiliation_strings":["New York University"],"raw_orcid":"https://orcid.org/0000-0003-0035-4266","affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073978798","display_name":"Jinyang Li","orcid":"https://orcid.org/0000-0002-9574-1746"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyang Li","raw_affiliation_strings":["New York University"],"raw_orcid":"https://orcid.org/0000-0002-9574-1746","affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":21.7492,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.99550859,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9961000084877014,"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":0.9943000078201294,"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/stateful-firewall","display_name":"Stateful firewall","score":0.8758318424224854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.744106650352478},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.38784340023994446},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.21211454272270203}],"concepts":[{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.8758318424224854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744106650352478},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.38784340023994446},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.21211454272270203},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3689031.3696086","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689031.3696086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth European Conference on Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2679398531","display_name":null,"funder_award_id":"2220407","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2734941459","https://openalex.org/W2798291715","https://openalex.org/W2979044977","https://openalex.org/W2982157693","https://openalex.org/W3012479151","https://openalex.org/W3037639655","https://openalex.org/W3095488153","https://openalex.org/W4206688953","https://openalex.org/W4321636575","https://openalex.org/W4372263604","https://openalex.org/W4387321091","https://openalex.org/W4388584589","https://openalex.org/W4388874804","https://openalex.org/W4401176373"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2583381754","https://openalex.org/W2144255176","https://openalex.org/W2222333653","https://openalex.org/W109977192","https://openalex.org/W1970797462","https://openalex.org/W2019740326","https://openalex.org/W2047113772"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,20,27],"wildly":[5],"popular":[6],"today":[7],"and":[8],"it":[9],"is":[10],"important":[11],"to":[12],"serve":[13],"them":[14],"efficiently.":[15],"Existing":[16],"LLM":[17],"serving":[18,51],"systems":[19],"stateless":[21],"across":[22],"requests.":[23],"Consequently,":[24],"when":[25],"LLMs":[26],"used":[28],"in":[29,57],"the":[30,40,50],"common":[31],"setting":[32],"of":[33,39],"multi-turn":[34],"conversations,":[35],"a":[36],"growing":[37],"log":[38],"conversation":[41],"history":[42],"must":[43],"be":[44],"processed":[45],"alongside":[46],"any":[47],"request":[48],"by":[49],"system":[52],"at":[53],"each":[54],"turn,":[55],"resulting":[56],"repeated":[58],"processing.":[59]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
