{"id":"https://openalex.org/W7134934897","doi":"https://doi.org/10.1145/3779212.3790119","title":"A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs","display_name":"A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134934897","doi":"https://doi.org/10.1145/3779212.3790119"},"language":null,"primary_location":{"id":"doi:10.1145/3779212.3790119","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790119","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 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3779212.3790119","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hongsun Jang","orcid":"https://orcid.org/0000-0003-4291-6124"},"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":"Hongsun Jang","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-4291-6124","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jaeyong Song","orcid":"https://orcid.org/0000-0001-9976-7487"},"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 Song","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-9976-7487","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Changmin Shin","orcid":"https://orcid.org/0009-0004-8242-8330"},"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":"Changmin Shin","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-8242-8330","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Si Ung Noh","orcid":"https://orcid.org/0009-0000-2228-2131"},"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":"Si Ung Noh","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-2228-2131","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jaewon Jung","orcid":"https://orcid.org/0000-0003-0770-9277"},"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":"Jaewon Jung","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0770-9277","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jisung Park","orcid":"https://orcid.org/0000-0002-1826-9003"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jisung Park","raw_affiliation_strings":["POSTECH, Pohang, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1826-9003","affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jinho Lee","orcid":"https://orcid.org/0000-0003-4010-6611"},"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":"Jinho Lee","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-4010-6611","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.39910000562667847,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.39910000562667847,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.08990000188350677,"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":0.039900001138448715,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7511000037193298},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5472000241279602},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4693000018596649},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4474000036716461},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4260999858379364},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.37049999833106995},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.3659000098705292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7515000104904175},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7511000037193298},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5472000241279602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5335999727249146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5246000289916992},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3050999939441681},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.266400009393692},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779212.3790119","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790119","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 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3779212.3790119","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790119","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 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2021890516","https://openalex.org/W2133718097","https://openalex.org/W2213235058","https://openalex.org/W2725159389","https://openalex.org/W3130240120","https://openalex.org/W3209568355","https://openalex.org/W4220660812","https://openalex.org/W4247512567","https://openalex.org/W4281689324","https://openalex.org/W4308083513","https://openalex.org/W4316660797","https://openalex.org/W4319870567","https://openalex.org/W4372263745","https://openalex.org/W4386566496","https://openalex.org/W4387321091","https://openalex.org/W4401211704","https://openalex.org/W4401212125","https://openalex.org/W4405755164","https://openalex.org/W4411471852","https://openalex.org/W4411486062","https://openalex.org/W4411486373"],"related_works":[],"abstract_inverted_index":{"The":[0],"computational":[1],"and":[2,37,60],"memory":[3,32,36],"demands":[4],"of":[5],"large":[6,51],"language":[7],"models":[8],"for":[9,15],"generative":[10],"inference":[11,23],"present":[12],"significant":[13],"challenges":[14],"practical":[16],"deployment.":[17],"One":[18],"promising":[19],"solution":[20],"targeting":[21],"offline":[22],"is":[24],"offloading-based":[25],"batched":[26],"inference,":[27],"which":[28],"extends":[29],"the":[30,50],"GPU's":[31],"hierarchy":[33],"with":[34,57],"host":[35],"storage.":[38],"However,":[39],"it":[40],"often":[41],"suffers":[42],"from":[43],"substantial":[44],"I/O":[45],"overhead,":[46],"primarily":[47],"due":[48],"to":[49],"KV":[52],"cache":[53],"sizes":[54],"that":[55],"scale":[56],"batch":[58],"size":[59],"context":[61],"window":[62],"length.":[63]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-11T00:00:00"}