{"id":"https://openalex.org/W4372267442","doi":"https://doi.org/10.1109/icassp49357.2023.10096632","title":"Quantpipe: Applying Adaptive Post-Training Quantization For Distributed Transformer Pipelines In Dynamic Edge Environments","display_name":"Quantpipe: Applying Adaptive Post-Training Quantization For Distributed Transformer Pipelines In Dynamic Edge Environments","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267442","doi":"https://doi.org/10.1109/icassp49357.2023.10096632"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100342598","display_name":"Haonan Wang","orcid":"https://orcid.org/0000-0001-8241-7982"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haonan Wang","raw_affiliation_strings":["University of Southern California,Department of Electrical and Computer Engineering,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003773058","display_name":"Connor Imes","orcid":"https://orcid.org/0000-0003-1683-8353"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Connor Imes","raw_affiliation_strings":["University of Southern California,Information Sciences Institute,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Sciences Institute,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076002956","display_name":"Souvik Kundu","orcid":"https://orcid.org/0000-0002-3533-9405"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Souvik Kundu","raw_affiliation_strings":["University of Southern California,Department of Electrical and Computer Engineering,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084205024","display_name":"Peter A. Beerel","orcid":"https://orcid.org/0000-0002-8283-0168"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter A. Beerel","raw_affiliation_strings":["University of Southern California,Department of Electrical and Computer Engineering,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022935102","display_name":"Stephen P. Crago","orcid":"https://orcid.org/0000-0002-5620-4227"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen P. Crago","raw_affiliation_strings":["University of Southern California,Department of Electrical and Computer Engineering,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023774940","display_name":"John Paul Walters","orcid":"https://orcid.org/0000-0001-5281-6237"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Paul Walters","raw_affiliation_strings":["University of Southern California,Information Sciences Institute,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Sciences Institute,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100342598"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.844,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74515188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9959999918937683,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9959999918937683,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9955999851226807,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7680617570877075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7194007635116577},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44195640087127686},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.42292261123657227},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.41725271940231323},{"id":"https://openalex.org/keywords/dynamic-range","display_name":"Dynamic range","score":0.414878249168396},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.401536762714386},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3761926591396332},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34726017713546753},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3295474350452423},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13816672563552856},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12601014971733093},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09195500612258911}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7680617570877075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7194007635116577},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44195640087127686},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.42292261123657227},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.41725271940231323},{"id":"https://openalex.org/C87133666","wikidata":"https://www.wikidata.org/wiki/Q1161699","display_name":"Dynamic range","level":2,"score":0.414878249168396},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.401536762714386},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3761926591396332},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34726017713546753},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3295474350452423},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13816672563552856},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12601014971733093},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09195500612258911},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2127941149","https://openalex.org/W2774000609","https://openalex.org/W2896457183","https://openalex.org/W2915478146","https://openalex.org/W2969388332","https://openalex.org/W2970601456","https://openalex.org/W2973727699","https://openalex.org/W2991040477","https://openalex.org/W3040573126","https://openalex.org/W3088912395","https://openalex.org/W3094502228","https://openalex.org/W3169545043","https://openalex.org/W3212135426","https://openalex.org/W4224227775","https://openalex.org/W4292779060","https://openalex.org/W4298422451","https://openalex.org/W4313496563","https://openalex.org/W4385245566","https://openalex.org/W6679154944","https://openalex.org/W6739901393","https://openalex.org/W6746839373","https://openalex.org/W6755207826","https://openalex.org/W6756718674","https://openalex.org/W6759144272","https://openalex.org/W6767298317","https://openalex.org/W6767997687","https://openalex.org/W6778883912","https://openalex.org/W6780805062","https://openalex.org/W6784333009","https://openalex.org/W6796414051"],"related_works":["https://openalex.org/W4386245174","https://openalex.org/W4200132709","https://openalex.org/W3198752256","https://openalex.org/W3183118997","https://openalex.org/W3214410901","https://openalex.org/W3204400881","https://openalex.org/W3204296682","https://openalex.org/W2917767146","https://openalex.org/W2973622361","https://openalex.org/W3176282186"],"abstract_inverted_index":{"Pipeline":[0],"parallelism":[1],"has":[2,15],"achieved":[3],"great":[4],"success":[5],"in":[6,11,19,23,34,70],"deploying":[7],"large-scale":[8],"transformer":[9,76],"models":[10],"cloud":[12,24],"environments,":[13],"but":[14],"received":[16],"less":[17],"attention":[18],"edge":[20,35,51],"environments.":[21],"Unlike":[22],"scenarios":[25],"with":[26,46,90],"high-speed":[27],"and":[28,106],"stable":[29],"network":[30],"inter-connects,":[31],"dynamic":[32,117],"bandwidth":[33,73,118],"systems":[36],"can":[37],"degrade":[38],"distributed":[39,50],"pipeline":[40,77,121],"performance.":[41],"We":[42,85],"address":[43],"this":[44],"issue":[45],"QuantPipe,":[47],"a":[48,91,125,130],"communication-efficient":[49],"system":[52],"that":[53,113],"introduces":[54],"post-training":[55],"quantization":[56,97,134,141],"(PTQ)":[57],"to":[58,67,72,116,119,147],"compress":[59],"the":[60,88,102],"communicated":[61],"tensors.":[62],"QuantPipe":[63,114],"uses":[64],"adaptive":[65],"PTQ":[66],"change":[68],"bitwidths":[69],"response":[71],"dynamics,":[74],"maintaining":[75],"performance":[78,122],"while":[79,123],"incurring":[80],"limited":[81],"inference":[82],"accuracy":[83,89,128,138],"loss.":[84],"further":[86],"improve":[87],"directed-search":[92],"analytical":[93],"clipping":[94],"for":[95],"integer":[96],"method":[98],"(DS-ACIQ),":[99],"which":[100],"bridges":[101],"gap":[103],"between":[104],"estimated":[105],"real":[107],"data":[108],"distributions.":[109],"Experimental":[110],"results":[111],"show":[112],"adapts":[115],"maintain":[120],"achieving":[124],"practical":[126],"model":[127],"using":[129],"wide":[131],"range":[132],"of":[133],"bitwidths,":[135],"e.g.,":[136],"improving":[137],"under":[139],"2-bit":[140],"by":[142],"15.85%":[143],"on":[144],"ImageNet":[145],"compared":[146],"naive":[148],"quantization.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}