{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:36:38Z","timestamp":1767339398429,"version":"3.37.3"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096632","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["Quantpipe: Applying Adaptive Post-Training Quantization For Distributed Transformer Pipelines In Dynamic Edge Environments"],"prefix":"10.1109","author":[{"given":"Haonan","family":"Wang","sequence":"first","affiliation":[{"name":"University of Southern California,Department of Electrical and Computer Engineering,USA"}]},{"given":"Connor","family":"Imes","sequence":"additional","affiliation":[{"name":"University of Southern California,Information Sciences Institute,USA"}]},{"given":"Souvik","family":"Kundu","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Electrical and Computer Engineering,USA"}]},{"given":"Peter A.","family":"Beerel","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Electrical and Computer Engineering,USA"}]},{"given":"Stephen P.","family":"Crago","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Electrical and Computer Engineering,USA"}]},{"given":"John","family":"Paul Walters","sequence":"additional","affiliation":[{"name":"University of Southern California,Information Sciences Institute,USA"}]}],"member":"263","reference":[{"key":"ref13","first-page":"4150","article-title":"Pipetransformer: automated elastic pipelining for distributed training of large-scale models","author":"he","year":"2021","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1145\/3341301.3359646"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/DSD57027.2022.00048"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/3485730.3493444"},{"key":"ref11","article-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism","volume":"32","author":"huang","year":"2019","journal-title":"Advances in neural information processing systems"},{"year":"2020","author":"lepikhin","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","key":"ref10"},{"year":"2020","author":"dosovitskiy","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","key":"ref2"},{"key":"ref1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"year":"2017","author":"lin","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","key":"ref17"},{"key":"ref16","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume":"32","author":"banner","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"7543","article-title":"Improving neural network quantization without retraining using outlier channel splitting","author":"zhao","year":"2019","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1038\/s41467-022-29763-x"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"year":"2019","author":"shoeybi","article-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","key":"ref7"},{"key":"ref9","article-title":"Communication efficient distributed machine learning with the parameter server","volume":"27","author":"li","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Pointer sentinel mixture models","author":"stephen","year":"2017","journal-title":"5th International Conference on Learning Representations (ICLR)"},{"key":"ref3","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of NAACL-HLT"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/SiPS50750.2020.9195240"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096632.pdf?arnumber=10096632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:00:45Z","timestamp":1700506845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096632\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096632","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}