{"id":"https://openalex.org/W4415159602","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1916","title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","display_name":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415159602","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1916"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1916","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1916","pdf_url":"https://aclanthology.org/2026.findings-acl.1916.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1916.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006469607","display_name":"Jiantong Jiang","orcid":"https://orcid.org/0000-0002-1624-3969"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiantong Jiang","raw_affiliation_strings":["The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101839046","display_name":"Pei\u2010Yu Yang","orcid":"https://orcid.org/0000-0002-2406-4055"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peiyu Yang","raw_affiliation_strings":["The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100421998","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-1055-7609"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100639398","display_name":"Feng Liu","orcid":"https://orcid.org/0000-0002-5005-9129"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.9771,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94961763,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"38450","last_page":"38476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9596999883651733,"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":0.9057999849319458,"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":[{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.49399998784065247},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.476500004529953},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4221999943256378},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.3822000026702881},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.35659998655319214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573999762535095},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.3822000026702881},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25450000166893005}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1916","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1916","pdf_url":"https://aclanthology.org/2026.findings-acl.1916.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"doi:10.36227/techrxiv.176046306.66521015/v1","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.176046306.66521015/v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.176046306.66521015/v1","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Techrxiv","raw_type":"posted-content"},{"id":"pmh:oai:arXiv.org:2607.08057","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.08057","pdf_url":"https://arxiv.org/pdf/2607.08057","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/366634","is_oa":false,"landing_page_url":"https://doi.org/10.36227/techrxiv.176046306.66521015/v1.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.48550/arxiv.2607.08057","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.08057","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1916","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1916","pdf_url":"https://aclanthology.org/2026.findings-acl.1916.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1063757644","display_name":"Collaborative Research: NSF-CSIRO: RESILIENCE: Graph Representation Learning for Fair Teaming in Crisis Response","funder_award_id":"2303037","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"},{"id":"https://openalex.org/F4320320386","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415159602.pdf","grobid_xml":"https://content.openalex.org/works/W4415159602.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,111],"rapid":[2],"advancements":[3],"of":[4],"large":[5],"language":[6],"models":[7],"(LLMs),":[8],"LLM":[9,32,105],"serving":[10,44,106],"systems":[11],"remain":[12],"memory-intensive":[13],"and":[14,64,68,71,73,81,98],"costly.The":[15],"keyvalue":[16],"(KV)":[17],"cache,":[18],"which":[19],"stores":[20],"KV":[21,41,100],"tensors":[22],"during":[23],"autoregressive":[24],"decoding,":[25],"is":[26,110],"crucial":[27],"for":[28,43,96],"enabling":[29],"low-latency,":[30],"high-throughput":[31],"inference":[33],"serving.In":[34],"this":[35],"survey,":[36],"we":[37,76],"focus":[38],"on":[39],"system-aware":[40],"infrastructure":[42],"LLMs":[45],"(abbreviated":[46],"as":[47],"sKis).We":[48],"revisit":[49],"recent":[50],"work":[51,87],"from":[52],"a":[53,89,94],"system":[54],"behavior":[55],"perspective,":[56],"organizing":[57],"existing":[58],"efforts":[59],"into":[60],"three":[61],"dimensions:":[62],"execution":[63],"scheduling":[65],"(temporal),":[66],"placement":[67],"migration":[69],"(spatial),":[70],"representation":[72],"retention":[74],"(structural).Furthermore,":[75],"analyze":[77],"cross-behavior":[78],"co-design":[79],"affinity":[80],"behavior-objective":[82],"links,":[83],"highlighting":[84],"future":[85],"opportunities.Our":[86],"systematizes":[88],"rapidly":[90],"evolving":[91],"area,":[92],"providing":[93],"foundation":[95],"understanding":[97],"innovating":[99],"cache":[101],"designs":[102],"in":[103],"modern":[104],"infrastructure.*":[107],"Peiyu":[108],"Yang":[109],"corresponding":[112],"author.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-14T00:00:00"}