{"id":"https://openalex.org/W4408844835","doi":"https://doi.org/10.1145/3689031.3696072","title":"Fast State Restoration in LLM Serving with HCache","display_name":"Fast State Restoration in LLM Serving with HCache","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4408844835","doi":"https://doi.org/10.1145/3689031.3696072"},"language":"en","primary_location":{"id":"doi:10.1145/3689031.3696072","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689031.3696072","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3689031.3696072","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109082020","display_name":"S.Y. Gao","orcid":"https://orcid.org/0009-0000-4751-0161"},"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":true,"raw_author_name":"Shiwei Gao","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028549167","display_name":"Youmin Chen","orcid":"https://orcid.org/0000-0003-4171-4299"},"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":"Youmin Chen","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101740783","display_name":"Jiwu Shu","orcid":"https://orcid.org/0000-0002-7362-2789"},"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":"Jiwu Shu","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109082020"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":14.1979,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9909979,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10378","display_name":"Advanced MRI Techniques and Applications","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10378","display_name":"Advanced MRI Techniques and Applications","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10049","display_name":"Magnetic properties of thin films","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5588456988334656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.554323673248291},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08131355047225952}],"concepts":[{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5588456988334656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.554323673248291},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08131355047225952}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3689031.3696072","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689031.3696072","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3689031.3696072","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689031.3696072","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth European Conference on Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G1674141309","display_name":null,"funder_award_id":"U22B2023,62202255","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G8407491233","display_name":null,"funder_award_id":"2022YFB4500302","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":17,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2606555609","https://openalex.org/W2776946878","https://openalex.org/W2969388332","https://openalex.org/W3027879771","https://openalex.org/W4220884018","https://openalex.org/W4287888039","https://openalex.org/W4318541673","https://openalex.org/W4323343906","https://openalex.org/W4381104068","https://openalex.org/W4387321090","https://openalex.org/W4387321091","https://openalex.org/W4388979610","https://openalex.org/W4389518760","https://openalex.org/W4393065402","https://openalex.org/W4394745423","https://openalex.org/W4401176373"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"growing":[1],"complexity":[2],"of":[3,28,35,50,74],"LLM":[4],"usage":[5],"today,":[6],"e.g.,":[7],"multi-round":[8],"conversation":[9],"and":[10,54],"retrieval-augmented":[11],"generation":[12],"(RAG),":[13],"makes":[14],"contextual":[15],"states":[16],"(i.e.,":[17],"KV":[18,52],"cache)":[19],"reusable":[20],"across":[21],"user":[22],"requests.":[23],"Given":[24],"the":[25,51,61],"capacity":[26],"constraints":[27],"GPU":[29,41],"memory,":[30],"only":[31],"a":[32],"limited":[33],"number":[34],"contexts":[36],"can":[37],"be":[38],"cached":[39],"on":[40],"for":[42,70],"reusing.":[43],"Existing":[44],"inference":[45],"systems":[46],"typically":[47],"evict":[48],"part":[49],"cache":[53],"restore":[55],"it":[56,59,66],"by":[57],"recomputing":[58],"from":[60],"original":[62],"tokens":[63],"or":[64,79],"offloading":[65],"to":[67],"host":[68],"storage":[69],"later":[71],"retrieval,":[72],"both":[73],"which":[75],"introduce":[76],"substantial":[77],"computational":[78],"I/O":[80],"overheads.":[81]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
