{"id":"https://openalex.org/W4416429885","doi":"https://doi.org/10.1109/iccad66269.2025.11240826","title":"LLM-on-the-Palm: Mobile LLM Inference with PIM-Enhanced NAND Flash Memory","display_name":"LLM-on-the-Palm: Mobile LLM Inference with PIM-Enhanced NAND Flash Memory","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W4416429885","doi":"https://doi.org/10.1109/iccad66269.2025.11240826"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-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/A5044389532","display_name":"H. Jin Kim","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":"Hyunjin Kim","raw_affiliation_strings":["Seoul National University,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074636159","display_name":"Sung\u2010Hee Han","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":false,"raw_author_name":"Sanghyeok Han","raw_affiliation_strings":["Seoul National University,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042758354","display_name":"Jae-Joon Kim","orcid":"https://orcid.org/0000-0003-1226-2537"},"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":"Jae-Joon Kim","raw_affiliation_strings":["Seoul National University,Seoul,Republic of Korea"],"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":3,"corresponding_author_ids":["https://openalex.org/A5044389532"],"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":0.50296994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.15549999475479126,"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"}},"topics":[{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.15549999475479126,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.08449999988079071,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.050200000405311584,"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/nand-gate","display_name":"NAND gate","score":0.6779999732971191},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.588699996471405},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5699999928474426},{"id":"https://openalex.org/keywords/flash","display_name":"Flash (photography)","score":0.5595999956130981},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5135999917984009},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5056999921798706},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.359499990940094},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3391999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731000185012817},{"id":"https://openalex.org/C124296912","wikidata":"https://www.wikidata.org/wiki/Q575178","display_name":"NAND gate","level":3,"score":0.6779999732971191},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.588699996471405},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C2777526259","wikidata":"https://www.wikidata.org/wiki/Q221836","display_name":"Flash (photography)","level":2,"score":0.5595999956130981},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5056999921798706},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4912000000476837},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4683000147342682},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C27670709","wikidata":"https://www.wikidata.org/wiki/Q5457555","display_name":"Flash file system","level":4,"score":0.2962000072002411},{"id":"https://openalex.org/C34172316","wikidata":"https://www.wikidata.org/wiki/Q499024","display_name":"Non-volatile random-access memory","level":5,"score":0.2784999907016754},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C131017901","wikidata":"https://www.wikidata.org/wiki/Q170451","display_name":"Logic gate","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C2779191767","wikidata":"https://www.wikidata.org/wiki/Q6887075","display_name":"Mobile cloud computing","level":3,"score":0.25279998779296875},{"id":"https://openalex.org/C2776531357","wikidata":"https://www.wikidata.org/wiki/Q174077","display_name":"Flash memory","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2142432849","https://openalex.org/W2296157284","https://openalex.org/W2517657787","https://openalex.org/W2768358071","https://openalex.org/W2792589388","https://openalex.org/W2966983573","https://openalex.org/W2982653262","https://openalex.org/W3006586535","https://openalex.org/W4251884961","https://openalex.org/W4308083518","https://openalex.org/W4308083751","https://openalex.org/W4360831773","https://openalex.org/W4387321091","https://openalex.org/W4392745629","https://openalex.org/W4393407029","https://openalex.org/W4394994587","https://openalex.org/W4398234863","https://openalex.org/W4400641571","https://openalex.org/W4402671659","https://openalex.org/W4404181049","https://openalex.org/W4404955137","https://openalex.org/W4406207083","https://openalex.org/W4406302454"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3],"inference":[4,71,85],"on":[5,35,134],"edge":[6],"devices":[7],"is":[8],"crucial":[9],"for":[10,73,113],"democratizing":[11],"AI":[12],"and":[13,16],"addressing":[14],"privacy":[15],"security":[17],"concerns":[18],"associated":[19],"with":[20,89],"cloud":[21],"services.":[22],"However,":[23],"the":[24,49,64],"large":[25],"parameter":[26],"sizes":[27],"of":[28,51,86],"LLMs":[29,88],"pose":[30],"significant":[31],"challenges":[32],"in":[33,104],"deployment":[34],"resource-constrained":[36],"devices,":[37],"affecting":[38],"user":[39],"experience.":[40],"Mobile":[41],"DRAM":[42],"typically":[43],"cannot":[44],"accommodate":[45],"these":[46],"parameters,":[47],"necessitating":[48],"use":[50],"NAND":[52,79,106],"flash":[53,80,107],"memory,":[54],"but":[55],"it":[56],"has":[57],"considerably":[58],"slower":[59],"access":[60],"speeds.":[61],"To":[62],"overcome":[63],"limitations,":[65],"we":[66],"propose":[67],"LLM-on-the-Palm,":[68],"an":[69,142],"LLM":[70],"system":[72],"smartphones":[74],"that":[75,125],"leverages":[76],"Processing-in-Memory":[77],"(PIM)-enhanced":[78],"memory":[81,108],"to":[82,141],"enable":[83],"fast":[84],"billion-parameter":[87],"minimal":[90],"hardware":[91],"modifications.":[92],"Our":[93],"approach":[94],"requires":[95],"only":[96],"a":[97,105,135],"single":[98],"multiply-accumulate":[99],"(MAC)":[100],"unit":[101],"per":[102,131],"plane":[103],"-":[109,117],"256":[110,114],"MAC":[111],"units":[112],"GB":[115],"SSD":[116],"without":[118],"compromising":[119],"cell":[120],"density.":[121],"Simulation":[122],"results":[123],"show":[124],"our":[126],"design":[127],"achieves":[128],"\u223c100":[129],"ms":[130],"token":[132],"generation":[133],"6.7B":[136],"model":[137],"under":[138],"specifications":[139],"similar":[140],"iPhone-15.":[143]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-20T00:00:00"}
