{"id":"https://openalex.org/W7084104154","doi":"https://doi.org/10.1145/3731569.3764823","title":"Jenga: Effective Memory Management for Serving LLM with Heterogeneity","display_name":"Jenga: Effective Memory Management for Serving LLM with Heterogeneity","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W7084104154","doi":"https://doi.org/10.1145/3731569.3764823"},"language":"en","primary_location":{"id":"doi:10.1145/3731569.3764823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764823","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731569.3764823","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0001-9045-9269"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, Beijing, China","UC Berkeley, Berkeley, California, USA"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"UC Berkeley, Berkeley, California, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kuntai Du","orcid":"https://orcid.org/0000-0002-3964-4079"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuntai Du","raw_affiliation_strings":["University of Chicago, Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shu Liu","orcid":"https://orcid.org/0009-0009-0825-6178"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shu Liu","raw_affiliation_strings":["UC Berkeley, Berkeley, California, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, California, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Woosuk Kwon","orcid":"https://orcid.org/0009-0008-8870-4892"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Woosuk Kwon","raw_affiliation_strings":["UC Berkeley, Berkeley, California, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, California, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangxi Mo","orcid":"https://orcid.org/0009-0007-4427-0036"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangxi Mo","raw_affiliation_strings":["UC Berkeley, Berkeley, California, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, California, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yufeng Wang","orcid":"https://orcid.org/0009-0008-9290-8978"},"institutions":[{"id":"https://openalex.org/I142600864","display_name":"College of San Mateo","ror":"https://ror.org/01gwn6z70","country_code":"US","type":"education","lineage":["https://openalex.org/I142600864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufeng Wang","raw_affiliation_strings":["Independent Researcher, San Mateo, California, USA"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, San Mateo, California, USA","institution_ids":["https://openalex.org/I142600864"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoxuan Liu","orcid":"https://orcid.org/0009-0004-4968-1027"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoxuan Liu","raw_affiliation_strings":["UC Berkeley, Berkeley, California, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, California, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaichao You","orcid":"https://orcid.org/0000-0002-1955-3743"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaichao You","raw_affiliation_strings":["Tsinghua University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhuohan Li","orcid":"https://orcid.org/0009-0004-1534-9106"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuohan Li","raw_affiliation_strings":["UC Berkeley, Berkeley, California, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, California, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingsheng Long","orcid":"https://orcid.org/0000-0002-5412-9120"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsheng Long","raw_affiliation_strings":["Tsinghua University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jidong Zhai","orcid":"https://orcid.org/0000-0002-7656-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Zhai","raw_affiliation_strings":["Tsinghua University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joseph Gonzalez","orcid":"https://orcid.org/0000-0003-2921-956X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Gonzalez","raw_affiliation_strings":["UC Berkeley, Berkeley, California, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, California, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ion Stoica","orcid":"https://orcid.org/0000-0002-5373-0088"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ion Stoica","raw_affiliation_strings":["UC Berkeley, Berkeley, California, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, California, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":13,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5849319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"446","last_page":"461"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12703","display_name":"Oil Palm Production and Sustainability","score":0.7172999978065491,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12703","display_name":"Oil Palm Production and Sustainability","score":0.7172999978065491,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11844","display_name":"Lipid metabolism and biosynthesis","score":0.10350000113248825,"subfield":{"id":"https://openalex.org/subfields/1303","display_name":"Biochemistry"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13361","display_name":"Coconut Research and Applications","score":0.029899999499320984,"subfield":{"id":"https://openalex.org/subfields/1604","display_name":"Inorganic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.376800000667572},{"id":"https://openalex.org/keywords/human-memory","display_name":"Human memory","score":0.3677999973297119},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33869999647140503},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.29420000314712524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6409000158309937},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.3873000144958496},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.376800000667572},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3725000023841858},{"id":"https://openalex.org/C2985957978","wikidata":"https://www.wikidata.org/wiki/Q492","display_name":"Human memory","level":3,"score":0.3677999973297119},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.25200000405311584},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731569.3764823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764823","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731569.3764823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764823","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"are":[3],"widely":[4],"used":[5],"but":[6],"expensive":[7],"to":[8,16],"run.":[9],"To":[10],"reduce":[11],"costs,":[12],"it":[13],"is":[14],"crucial":[15],"maximize":[17],"request":[18],"batch":[19],"size":[20],"through":[21],"efficient":[22],"GPU":[23],"memory":[24],"management.":[25],"Existing":[26],"approaches,":[27],"such":[28],"as":[29],"PagedAttention,":[30],"struggle":[31],"with":[32],"modern":[33],"LLMs":[34],"because":[35],"of":[36,43],"the":[37,41],"growing":[38],"heterogeneity":[39],"in":[40],"sizes":[42],"models'":[44],"internal":[45],"embeddings":[46],"and":[47],"attention":[48],"mechanisms.":[49]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
