{"id":"https://openalex.org/W4411309330","doi":"https://doi.org/10.1145/3744244","title":"HAPE: Hardware-Aware LLM Pruning For Efficient On-Device Inference Optimization","display_name":"HAPE: Hardware-Aware LLM Pruning For Efficient On-Device Inference Optimization","publication_year":2025,"publication_date":"2025-06-14","ids":{"openalex":"https://openalex.org/W4411309330","doi":"https://doi.org/10.1145/3744244"},"language":"en","primary_location":{"id":"doi:10.1145/3744244","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744244","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3744244","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013503446","display_name":"Wenqian Zhao","orcid":"https://orcid.org/0000-0001-9501-9254"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Wenqian Zhao","raw_affiliation_strings":["The Chinese University of Hong Kong","The Chinese University of Hong Kong,  Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9501-9254","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong,  Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092876716","display_name":"Lancheng Zou","orcid":"https://orcid.org/0009-0004-6820-7064"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lancheng Zou","raw_affiliation_strings":["The Chinese University of Hong Kong","The Chinese University of Hong Kong,  Hong Kong Hong Kong"],"raw_orcid":"https://orcid.org/0009-0004-6820-7064","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong,  Hong Kong Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032567340","display_name":"Zixiao Wang","orcid":"https://orcid.org/0009-0000-8179-0996"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zixiao Wang","raw_affiliation_strings":["Computer Science and Engineering, The Chinese University of Hong Kong","Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0000-8179-0996","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033561795","display_name":"Xufeng Yao","orcid":"https://orcid.org/0000-0002-7994-6290"},"institutions":[{"id":"https://openalex.org/I2800531931","display_name":"Hong Kong College of Technology","ror":"https://ror.org/014w0p014","country_code":"CN","type":"education","lineage":["https://openalex.org/I2800531931"]},{"id":"https://openalex.org/I4210140242","display_name":"Cyber University of Korea","ror":"https://ror.org/03t85np98","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210140242"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK","KR"],"is_corresponding":false,"raw_author_name":"Xufeng Yao","raw_affiliation_strings":["Computer Science and Engineering, CUHK","Computer Science and Engineering, CUHK, Hong Kong Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-7994-6290","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, CUHK","institution_ids":["https://openalex.org/I4210140242","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Computer Science and Engineering, CUHK, Hong Kong Hong Kong","institution_ids":["https://openalex.org/I2800531931","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051340429","display_name":"Bei Yu","orcid":"https://orcid.org/0000-0001-6406-4810"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bei Yu","raw_affiliation_strings":["The Chinese University of Hong Kong Department of Computer Science and Engineering","The Chinese University of Hong Kong Department of Computer Science and Engineering,  Hong Kong Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-6406-4810","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong Department of Computer Science and Engineering,  Hong Kong Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013503446"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":6.2003,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96001636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"30","issue":"4","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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":0.9973000288009644,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9968000054359436,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.9259172677993774},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7396037578582764},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6434502601623535},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.5273573994636536},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4602258801460266},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38446474075317383},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3656373918056488},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.36161088943481445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32828250527381897},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32225745916366577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9259172677993774},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7396037578582764},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6434502601623535},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.5273573994636536},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4602258801460266},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38446474075317383},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3656373918056488},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36161088943481445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32828250527381897},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32225745916366577},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3744244","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744244","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3744244","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744244","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2343954916","https://openalex.org/W2599674900","https://openalex.org/W2750779823","https://openalex.org/W2890894339","https://openalex.org/W2946609015","https://openalex.org/W2954698171","https://openalex.org/W2996908057","https://openalex.org/W2998617917","https://openalex.org/W3095319910","https://openalex.org/W3105966348","https://openalex.org/W3177525997","https://openalex.org/W3211878177","https://openalex.org/W4200145863","https://openalex.org/W4224903119","https://openalex.org/W4385573119","https://openalex.org/W4386108430","https://openalex.org/W4393160252","https://openalex.org/W6739901393","https://openalex.org/W6775706467","https://openalex.org/W6803320286","https://openalex.org/W6893809404"],"related_works":["https://openalex.org/W2373300491","https://openalex.org/W2395294869","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W2355171581","https://openalex.org/W4229439743"],"abstract_inverted_index":{"Over":[0],"the":[1,42,59,65,141,196],"past":[2],"few":[3],"years,":[4],"large":[5,57],"language":[6],"models":[7],"(LLMs)":[8],"have":[9,76,95],"demonstrated":[10],"remarkable":[11],"performance":[12],"and":[13,32,74,92,109,145,185,201,211],"versatility":[14,91],"across":[15],"a":[16,37,97,124,192],"variety":[17],"of":[18,62,67,80,90,111,114],"complex":[19],"tasks.":[20],"However,":[21],"their":[22,28],"deployment":[23,66,108],"has":[24],"been":[25],"challenged":[26],"by":[27,163],"substantial":[29],"model":[30,43],"size":[31],"computational":[33],"requirements.":[34],"Pruning":[35],"is":[36,171],"effective":[38],"approach":[39],"to":[40,84,105,122,153],"make":[41],"parameters":[44],"sparse,":[45],"thereby":[46,202],"acquire":[47],"inference":[48,110,130,209],"acceleration.":[49],"While":[50],"not":[51],"everyone":[52],"requires":[53],"training":[54,200],"or":[55],"fine-tuning":[56],"models,":[58],"diverse":[60,208],"range":[61],"applications":[63],"necessitates":[64],"LLMs":[68],"on":[69,214],"different":[70],"devices.":[71],"Model":[72],"pruning":[73,99,125,135,143,151],"compression":[75],"emerged":[77],"as":[78],"areas":[79],"deep":[81],"research":[82],"interest":[83],"address":[85],"these":[86],"challenges.":[87],"In":[88],"consideration":[89],"practicality,":[93],"we":[94,119,160],"designed":[96],"hardware-aware":[98],"process":[100,189],"for":[101,198],"general-purpose":[102],"hardware/edge":[103],"devices":[104],"enable":[106],"efficient":[107],"LLMs.":[112],"Instead":[113],"considering":[115],"sparse":[116],"ratio":[117],"alone,":[118],"are":[120],"motivated":[121],"design":[123],"framework":[126,139],"that":[127],"incorporates":[128],"genuine":[129],"speed-up":[131],"sensitivity":[132],"from":[133,158],"each":[134],"structure.":[136],"Moreover,":[137],"our":[138],"breaks":[140],"layer-by-layer":[142],"setting":[144],"fuse":[146],"several":[147],"layers":[148],"into":[149],"one":[150],"stage":[152],"allow":[154],"cross-layer":[155],"optimization.":[156,187],"Apart":[157],"that,":[159],"hold":[161],"pragmatism":[162],"conducting":[164],"compilation":[165],"optimization":[166],"during":[167],"pruning.":[168],"This":[169],"step":[170],"critical":[172],"because":[173],"most":[174],"sparsity":[175],"patterns":[176],"barely":[177],"show":[178],"distinct":[179],"speed":[180,210],"acceleration":[181],"with":[182],"corresponding":[183],"dataflow":[184],"memory":[186],"Our":[188],"operates":[190],"within":[191],"post-training":[193],"framework,":[194],"obviating":[195],"need":[197],"additional":[199],"reducing":[203],"resource":[204],"requirements,":[205],"while":[206],"ensuring":[207],"accuracy":[212],"requirements":[213],"hardware.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}