{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:37:42Z","timestamp":1782833862436,"version":"3.54.5"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"13","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004834","name":"Universitat Jaume I","doi-asserted-by":"publisher","award":["UJI-2023-04"],"award-info":[{"award-number":["UJI-2023-04"]}],"id":[{"id":"10.13039\/501100004834","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003359","name":"Generalitat Valenciana","doi-asserted-by":"publisher","award":["CIAPOS\/2023\/431"],"award-info":[{"award-number":["CIAPOS\/2023\/431"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci?n","doi-asserted-by":"crossref","award":["PID2023-146569NB-C2"],"award-info":[{"award-number":["PID2023-146569NB-C2"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci?n","doi-asserted-by":"crossref","award":["RYC2021-033973-I"],"award-info":[{"award-number":["RYC2021-033973-I"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100011011","name":"Junta de Andaluc?a","doi-asserted-by":"publisher","award":["POSTDOC2100025"],"award-info":[{"award-number":["POSTDOC2100025"]}],"id":[{"id":"10.13039\/501100011011","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,7,1]]},"DOI":"10.1109\/jiot.2025.3560382","type":"journal-article","created":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T13:40:14Z","timestamp":1744638014000},"page":"25676-25690","source":"Crossref","is-referenced-by-count":4,"title":["Latency-Critical Quantized Inference With Transformer Decoders on ARM and RISC-V CPUs"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5891-4479","authenticated-orcid":false,"given":"H\u00e9ctor","family":"Mart\u00ednez","sequence":"first","affiliation":[{"name":"Electronic and Computer Engineering, Universidad de C&#x00F3;rdoba, C&#x00F3;rdoba, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9321-2728","authenticated-orcid":false,"given":"Sandra","family":"Catal\u00e1n","sequence":"additional","affiliation":[{"name":"Computer Science and Egineering, Universitat Jaume I de Castell&#x00F3;n, Castell&#x00F3;n de la Plana, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8576-8451","authenticated-orcid":false,"given":"Adri\u00e1n","family":"Castell\u00f3","sequence":"additional","affiliation":[{"name":"DISCA, Universitat Polit&#x00E8;cnica de Val&#x00E8;ncia, Val&#x00E8;ncia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5954-4131","authenticated-orcid":false,"given":"Jose I.","family":"Mestre","sequence":"additional","affiliation":[{"name":"Computer Science and Egineering, Universitat Jaume I de Castell&#x00F3;n, Castell&#x00F3;n de la Plana, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5454-165X","authenticated-orcid":false,"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[{"name":"DISCA, Universitat Polit&#x00E8;cnica de Val&#x00E8;ncia, Val&#x00E8;ncia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"A survey of large language models","author":"Zhao","year":"2025","journal-title":"arXiv:2303.18223"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926296"},{"issue":"1","key":"ref4","first-page":"6869","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"Hubara","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","article-title":"Full stack optimization of transformer inference: A survey","author":"Kim","year":"2023","journal-title":"arXiv:2302.14017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref7","article-title":"Optimizing inference performance of transformers on CPUs","author":"Dice","year":"2021","journal-title":"arXiv:2102.06621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2023.102990"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3280805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-69766-1_26"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00027"},{"key":"ref12","volume-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref13","first-page":"30318","article-title":"LLM.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Dettmers"},{"key":"ref14","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref15","volume-title":"Triple-channel, high-side measurement, shunt and bus voltage monitor with I2C- and SMBUS-compatible interface","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1377603.1377607"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2925987"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2755561"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.110"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3638532"},{"key":"ref23","article-title":"I-BERT: Integer-only BERT Quantization","author":"Kim","year":"2021","journal-title":"arXiv:2101.01321"},{"key":"ref24","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv:1609.07843"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11045559\/10964275.pdf?arnumber=10964275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T21:09:40Z","timestamp":1771362580000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10964275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":24,"journal-issue":{"issue":"13"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3560382","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]}}}