{"id":"https://openalex.org/W7118619038","doi":"https://doi.org/10.1016/j.sysarc.2026.103699","title":"KVC-Q: A high-fidelity and dynamic KV Cache quantization framework for long-context large language models","display_name":"KVC-Q: A high-fidelity and dynamic KV Cache quantization framework for long-context large language models","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7118619038","doi":"https://doi.org/10.1016/j.sysarc.2026.103699"},"language":"en","primary_location":{"id":"doi:10.1016/j.sysarc.2026.103699","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.sysarc.2026.103699","pdf_url":null,"source":{"id":"https://openalex.org/S127660348","display_name":"Journal of Systems Architecture","issn_l":"1383-7621","issn":["1383-7621","1873-6165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems Architecture","raw_type":"journal-article"},"type":"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/A5122037790","display_name":"Yusen Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I83791580","display_name":"Fujian University of Technology","ror":"https://ror.org/03c8fdb16","country_code":"CN","type":"education","lineage":["https://openalex.org/I83791580"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusen Wu","raw_affiliation_strings":["Fujian University of Technology, Fuzhou, China"],"affiliations":[{"raw_affiliation_string":"Fujian University of Technology, Fuzhou, China","institution_ids":["https://openalex.org/I83791580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122043034","display_name":"Ruiqin Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I83791580","display_name":"Fujian University of Technology","ror":"https://ror.org/03c8fdb16","country_code":"CN","type":"education","lineage":["https://openalex.org/I83791580"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqin Lin","raw_affiliation_strings":["Fujian University of Technology, Fuzhou, China"],"affiliations":[{"raw_affiliation_string":"Fujian University of Technology, Fuzhou, China","institution_ids":["https://openalex.org/I83791580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122138315","display_name":"Jiarong Que","orcid":null},"institutions":[{"id":"https://openalex.org/I83791580","display_name":"Fujian University of Technology","ror":"https://ror.org/03c8fdb16","country_code":"CN","type":"education","lineage":["https://openalex.org/I83791580"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarong Que","raw_affiliation_strings":["Fujian University of Technology, Fuzhou, China"],"affiliations":[{"raw_affiliation_string":"Fujian University of Technology, Fuzhou, China","institution_ids":["https://openalex.org/I83791580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122200501","display_name":"Qixiang Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I83791580","display_name":"Fujian University of Technology","ror":"https://ror.org/03c8fdb16","country_code":"CN","type":"education","lineage":["https://openalex.org/I83791580"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixiang Zeng","raw_affiliation_strings":["Fujian University of Technology, Fuzhou, China"],"affiliations":[{"raw_affiliation_string":"Fujian University of Technology, Fuzhou, China","institution_ids":["https://openalex.org/I83791580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122062374","display_name":"Hongsen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I83791580","display_name":"Fujian University of Technology","ror":"https://ror.org/03c8fdb16","country_code":"CN","type":"education","lineage":["https://openalex.org/I83791580"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongsen Zhang","raw_affiliation_strings":["Fujian University of Technology, Fuzhou, China"],"affiliations":[{"raw_affiliation_string":"Fujian University of Technology, Fuzhou, China","institution_ids":["https://openalex.org/I83791580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5122062374"],"corresponding_institution_ids":["https://openalex.org/I83791580"],"apc_list":{"value":2800,"currency":"USD","value_usd":2800},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.041092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"173","issue":null,"first_page":"103699","last_page":"103699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.39399999380111694,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.39399999380111694,"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"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.14659999310970306,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.07410000264644623,"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":0.6606000065803528},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.5633999705314636},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5297999978065491},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.507099986076355},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4749999940395355},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4740999937057495},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3797000050544739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9093999862670898},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6606000065803528},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5297999978065491},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3797000050544739},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36570000648498535},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.2759999930858612},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.sysarc.2026.103699","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.sysarc.2026.103699","pdf_url":null,"source":{"id":"https://openalex.org/S127660348","display_name":"Journal of Systems Architecture","issn_l":"1383-7621","issn":["1383-7621","1873-6165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems Architecture","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2964110616","https://openalex.org/W3137147200"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2026-01-08T00:00:00"}
