{"id":"https://openalex.org/W4401568153","doi":"https://doi.org/10.23919/date58400.2024.10546617","title":"Communication-Efficient Model Parallelism for Distributed In-Situ Transformer Inference","display_name":"Communication-Efficient Model Parallelism for Distributed In-Situ Transformer Inference","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4401568153","doi":"https://doi.org/10.23919/date58400.2024.10546617"},"language":"en","primary_location":{"id":"doi:10.23919/date58400.2024.10546617","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation &amp;amp; Test in Europe Conference &amp;amp; Exhibition (DATE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110558003","display_name":"Yuanxin Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanxin Wei","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021061004","display_name":"Shengyuan Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyuan Ye","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048148542","display_name":"Jiazhi Jiang","orcid":"https://orcid.org/0000-0002-1417-3012"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazhi Jiang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385692","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0001-9943-6020"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041534890","display_name":"Dan Huang","orcid":"https://orcid.org/0000-0001-5582-1031"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024085713","display_name":"Jiangsu Du","orcid":"https://orcid.org/0000-0003-4707-9492"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangsu Du","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9300000071525574,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9300000071525574,"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/computer-science","display_name":"Computer science","score":0.74882972240448},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5582239627838135},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5474449396133423},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47044581174850464},{"id":"https://openalex.org/keywords/in-situ","display_name":"In situ","score":0.43333712220191956},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.41007667779922485},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37974491715431213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11340734362602234},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0877542495727539},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0700400173664093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74882972240448},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5582239627838135},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5474449396133423},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47044581174850464},{"id":"https://openalex.org/C2777822432","wikidata":"https://www.wikidata.org/wiki/Q216681","display_name":"In situ","level":2,"score":0.43333712220191956},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.41007667779922485},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37974491715431213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11340734362602234},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0877542495727539},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0700400173664093},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date58400.2024.10546617","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation &amp;amp; Test in Europe Conference &amp;amp; Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8699966540","display_name":null,"funder_award_id":"2021 YFB0301300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2127941149","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2963748441","https://openalex.org/W2991040477","https://openalex.org/W3108109508","https://openalex.org/W4385245566","https://openalex.org/W4385571616","https://openalex.org/W6679154944","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2045183646","https://openalex.org/W2162409446","https://openalex.org/W2109463584","https://openalex.org/W2504075107","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093","https://openalex.org/W1595672120","https://openalex.org/W4230999561"],"abstract_inverted_index":{"Transformer":[0,62,74,110],"models":[1],"have":[2],"shown":[3],"significant":[4],"success":[5],"in":[6],"a":[7,28,48,106,120,136,168,207],"wide":[8],"range":[9],"of":[10,31,42,51,73,97,129],"tasks.":[11],"Meanwhile,":[12],"massive":[13],"resources":[14],"required":[15],"by":[16,166,188],"its":[17,33],"inference":[18,63,111,186],"prevent":[19],"scenarios":[20],"with":[21,54,125,135,143],"resource-constrained":[22],"devices":[23,53],"from":[24],"in-situ":[25,109],"deployment,":[26],"leaving":[27],"high":[29],"threshold":[30],"integrating":[32],"advances.":[34],"Observing":[35],"that":[36,181],"these":[37],"scenarios,":[38],"e.g.":[39],"smart":[40],"home":[41],"edge":[43,98,114],"computing,":[44],"are":[45],"usually":[46],"comprise":[47],"rich":[49],"set":[50],"trusted":[52],"untapped":[55],"resources,":[56],"it":[57],"is":[58,117],"promising":[59],"to":[60,69,83,139,159,190,194],"distribute":[61],"onto":[64],"multiple":[65],"devices.":[66],"However,":[67],"due":[68],"the":[70,126,131,140,162,195],"tightly-coupled":[71],"feature":[72],"model,":[75],"existing":[76],"model":[77,148,209],"parallelism":[78,123,149],"approaches":[79],"necessitate":[80],"frequent":[81],"communication":[82,171],"resolve":[84],"data":[85],"dependencies,":[86],"making":[87],"them":[88],"unacceptable":[89],"for":[90,113],"distributed":[91,108,185],"inference,":[92],"especially":[93],"under":[94],"weak":[95],"interconnect":[96],"scenarios.":[99,115],"In":[100],"this":[101],"paper,":[102],"we":[103],"propose":[104],"DeTransformer,":[105],"communication-efficient":[107],"system":[112],"DeTransformer":[116,153,182],"based":[118],"on":[119,198],"novel":[121],"block":[122,138],"approach,":[124],"key":[127],"idea":[128],"restructuring":[130],"original":[132],"Trans-former":[133],"layer":[134,142],"single":[137],"decoupled":[141],"multi-ple":[144],"sub-blocks":[145],"and":[146,175,206],"exploit":[147],"between":[150],"sub-blocks.":[151],"Next,":[152],"contains":[154],"an":[155],"adaptive":[156],"placement":[157,164],"approach":[158,197],"automatically":[160],"select":[161],"optimal":[163],"strategy":[165],"striking":[167],"trade-off":[169],"among":[170],"capability,":[172],"computing":[173],"power":[174],"memory":[176],"budget.":[177],"Experimental":[178],"results":[179],"show":[180],"can":[183],"reduce":[184],"latency":[187],"up":[189],"2.81":[191],"x":[192],"compared":[193],"SOTA":[196],"4":[199],"devices,":[200],"while":[201],"effectively":[202],"maintaining":[203],"task":[204],"accuracy":[205],"consistent":[208],"size.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
