{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T06:50:52Z","timestamp":1781851852594,"version":"3.54.5"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008048","name":"Nanjing University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008048","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,24]]},"DOI":"10.1109\/iscas66217.2026.11562248","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:06:41Z","timestamp":1781813201000},"page":"1087-1091","source":"Crossref","is-referenced-by-count":0,"title":["UniMAC: Multi-Precision MAC with a Unified Computing Architecture for Efficient Large Language Model Inference"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Cong","sequence":"first","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juntao","family":"Liu","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xulong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Geng","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Du","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Du","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref2","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device llm compression and acceleration","volume-title":"Proceedings of machine learning and systems","volume":"6","author":"Lin"},{"key":"ref3","article-title":"Daq: Density-aware post-training weight-only quantization for llms","author":"Luo","year":"2024"},{"key":"ref4","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International conference on machine learning","author":"Xiao"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1970"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1065"},{"key":"ref7","article-title":"Qqq: Quality quattuor-bit quantization for large language models","author":"Zhang","year":"2024"},{"key":"ref8","first-page":"196","article-title":"Atom: Low-bit quantization for efficient and accurate llm serving","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Zhao"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3180"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.3044752"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2021.3128435"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3583781.3590269"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2023.3322259"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2024.3497724"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00110"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00064"},{"key":"ref17","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref18","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.sustainlp-1.6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sustainlp-1.5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530585"},{"key":"ref23","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"issue":"8","key":"ref24","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref25","article-title":"Pointer sentinel mixture models","volume-title":"International Conference on Learning Representations","author":"Merity"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075835"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2017.2767624"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2964234"}],"event":{"name":"2026 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"Shanghai, China","start":{"date-parts":[[2026,5,24]]},"end":{"date-parts":[[2026,5,28]]}},"container-title":["2026 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11561899\/11561804\/11562248.pdf?arnumber=11562248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:53:35Z","timestamp":1781848415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11562248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iscas66217.2026.11562248","relation":{},"subject":[],"published":{"date-parts":[[2026,5,24]]}}}