{"id":"https://openalex.org/W7160203323","doi":"https://doi.org/10.1109/lca.2026.3689575","title":"KiF: Accelerating Low-Batch LLM Inference Using In-Flash KV Cache","display_name":"KiF: Accelerating Low-Batch LLM Inference Using In-Flash KV Cache","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160203323","doi":"https://doi.org/10.1109/lca.2026.3689575"},"language":null,"primary_location":{"id":"doi:10.1109/lca.2026.3689575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2026.3689575","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","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/A5135150652","display_name":"Haeeun Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Haeeun Jung","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0003-7359-2676","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369475","display_name":"Jaeyong Lee","orcid":"https://orcid.org/0000-0003-3630-5933"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeyong Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-2724-8888","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088119205","display_name":"S.J. Lee","orcid":"https://orcid.org/0000-0003-2295-6591"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanggu Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135198018","display_name":"Huiwon Yun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huiwon Yun","raw_affiliation_strings":["Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0000-2549-3364","affiliations":[{"raw_affiliation_string":"Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053248335","display_name":"Dongsuk Jeon","orcid":"https://orcid.org/0000-0002-0395-8076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongsuk Jeon","raw_affiliation_strings":["Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0395-8076","affiliations":[{"raw_affiliation_string":"Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135209267","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Sung Kim","raw_affiliation_strings":["Department of Electrical &#x0026; Computer Engineering, University of Illinois, Urbana-Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-0442-5634","affiliations":[{"raw_affiliation_string":"Department of Electrical &#x0026; Computer Engineering, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062560097","display_name":"Jihong Kim","orcid":"https://orcid.org/0000-0002-7977-9883"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihong Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-7977-9883","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5135150652"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79842037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"1","first_page":"174","last_page":"177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.7645000219345093,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.7645000219345093,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.10360000282526016,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.023900000378489494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5321000218391418},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.37720000743865967},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.26460000872612},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.2637999951839447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115000128746033},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30640000104904175},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2026.3689575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2026.3689575","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"LLMs":[1],"on":[2],"edge":[3],"devices":[4],"is":[5],"constrained":[6],"by":[7],"the":[8,15,39,48],"memory-intensive,":[9],"dynamic":[10],"KV":[11,16,49,60],"cache.":[12,50],"While":[13],"offloading":[14,86],"cache":[17,61],"to":[18,37,47,79],"SSDs":[19],"expands":[20],"capacity,":[21],"it":[22],"introduces":[23],"severe":[24],"bandwidth":[25],"bottlenecks.":[26],"Existing":[27],"in-flash":[28,73],"processing":[29],"(IFP)":[30],"solutions,":[31],"optimized":[32],"for":[33],"static":[34],"weights,":[35],"fail":[36],"address":[38],"write-intensive":[40],"nature":[41],"and":[42,71],"access":[43],"pattern":[44],"mismatches":[45],"inherent":[46],"We":[51],"propose":[52],"KiF,":[53],"a":[54],"novel":[55],"IFP":[56],"solution":[57],"that":[58],"manages":[59],"within":[62],"flash":[63],"chips,":[64],"via":[65],"reliable":[66],"pseudo-SLC":[67],"based":[68],"write":[69],"management":[70],"specialized":[72],"GEMV":[74],"accelerator.":[75],"KiF":[76],"delivers":[77],"up":[78],"4.1\u00d7":[80],"higher":[81],"throughput":[82],"than":[83],"existing":[84],"SSD":[85],"solutions.":[87]},"counts_by_year":[],"updated_date":"2026-05-23T06:10:36.450269","created_date":"2026-05-05T00:00:00"}
