{"id":"https://openalex.org/W4407196790","doi":"https://doi.org/10.1145/3669940.3707239","title":"Fast On-device LLM Inference with NPUs","display_name":"Fast On-device LLM Inference with NPUs","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407196790","doi":"https://doi.org/10.1145/3669940.3707239"},"language":"en","primary_location":{"id":"doi:10.1145/3669940.3707239","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3669940.3707239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","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/A5034382142","display_name":"Daliang Xu","orcid":"https://orcid.org/0000-0002-6775-0688"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Daliang Xu","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6775-0688","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Zhang","orcid":"https://orcid.org/0009-0007-1107-4688"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-1107-4688","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101655748","display_name":"Liming Yang","orcid":"https://orcid.org/0009-0009-1163-028X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Yang","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-1163-028X","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010428676","display_name":"Ruiqi Liu","orcid":"https://orcid.org/0009-0004-3188-0976"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqi Liu","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3188-0976","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101617703","display_name":"Gang Huang","orcid":"https://orcid.org/0000-0002-4686-3181"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Huang","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China, & National Key Laboratory of Data Space Technology and System, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4686-3181","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China, & National Key Laboratory of Data Space Technology and System, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089690212","display_name":"Mengwei Xu","orcid":"https://orcid.org/0000-0001-6271-6993"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengwei Xu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6271-6993","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052249316","display_name":"Xuanzhe Liu","orcid":"https://orcid.org/0000-0002-7908-8484"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanzhe Liu","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7908-8484","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5034382142"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":21.6266,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.99362518,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"445","last_page":"462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9832000136375427,"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":0.9832000136375427,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9542999863624573,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9269999861717224,"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/inference","display_name":"Inference","score":0.6306217908859253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6287829875946045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31742358207702637}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6306217908859253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6287829875946045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31742358207702637}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3669940.3707239","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3669940.3707239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3791636283","display_name":null,"funder_award_id":"62325201","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":46,"referenced_works":["https://openalex.org/W1595548352","https://openalex.org/W2014168043","https://openalex.org/W2582073145","https://openalex.org/W2626129225","https://openalex.org/W2734941459","https://openalex.org/W2798467024","https://openalex.org/W2889402930","https://openalex.org/W2890894339","https://openalex.org/W2903650079","https://openalex.org/W2931092525","https://openalex.org/W2946609015","https://openalex.org/W2954698171","https://openalex.org/W2963015836","https://openalex.org/W2963122961","https://openalex.org/W2984200518","https://openalex.org/W2996874060","https://openalex.org/W2999276659","https://openalex.org/W3008374555","https://openalex.org/W3088076788","https://openalex.org/W3101962329","https://openalex.org/W3104849992","https://openalex.org/W3108212103","https://openalex.org/W3143446705","https://openalex.org/W3159727696","https://openalex.org/W3163966209","https://openalex.org/W3174661481","https://openalex.org/W3180037928","https://openalex.org/W3215427016","https://openalex.org/W4205983429","https://openalex.org/W4214951654","https://openalex.org/W4236853429","https://openalex.org/W4251637954","https://openalex.org/W4281651027","https://openalex.org/W4306178406","https://openalex.org/W4308083911","https://openalex.org/W4362471656","https://openalex.org/W4387212306","https://openalex.org/W4389500478","https://openalex.org/W4391623920","https://openalex.org/W4394871722","https://openalex.org/W4399121418","https://openalex.org/W4399140776","https://openalex.org/W4399323669","https://openalex.org/W4399534502","https://openalex.org/W4402670538","https://openalex.org/W4405418476"],"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":{"On-device":[0],"inference":[1,30],"for":[2],"Large":[3],"Language":[4],"Models":[5],"(LLMs),":[6],"driven":[7],"by":[8,34],"increasing":[9],"privacy":[10],"concerns":[11],"and":[12],"advancements":[13],"of":[14],"mobile-sized":[15,23],"models,":[16],"has":[17],"gained":[18],"significant":[19],"interest.":[20],"However,":[21],"even":[22],"LLMs":[24],"(e.g.,":[25],"Gemma-2B)":[26],"encounter":[27],"unacceptably":[28],"high":[29],"latency,":[31],"often":[32],"bottlenecked":[33],"the":[35],"prefill":[36],"stage":[37],"in":[38],"tasks":[39],"like":[40],"screen":[41],"UI":[42],"understanding.":[43]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}