{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T16:09:23Z","timestamp":1769011763313,"version":"3.49.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11132610","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["ReaLM: Reliable and Efficient Large Language Model Inference with Statistical Algorithm-Based Fault Tolerance"],"prefix":"10.1109","author":[{"given":"Tong","family":"Xie","sequence":"first","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]},{"given":"Jiawang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence,Beijing,China"}]},{"given":"Zishen","family":"Wan","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,GA,USA"}]},{"given":"Zuodong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]},{"given":"Yuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]},{"given":"Runsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]},{"given":"Ru","family":"Huang","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]},{"given":"Meng","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref2","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv:2303.18223"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iolts59296.2023.10224872"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3300376"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2017.2783333"},{"key":"ref8","first-page":"12","article-title":"Variability-and reliability-aware design for 16\/14 nm and beyond technology","volume-title":"Proc. IEDM","author":"Huang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2018.2884460"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218697"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2003.1253179"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2841824"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196129"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC47756.2020.9045479"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8714885"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8341970"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317870"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1984.1676475"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001208"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.7873\/DATE.2015.0303"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662389"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323816"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640420"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203882"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3195997"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE52982.2021.00025"},{"key":"ref28","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2205.01068"},{"key":"ref29","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref30","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. ICML","author":"Xiao"},{"key":"ref31","article-title":"Awq: Activation-aware weight quantization for 1 lm compression and acceleration","author":"Lin","year":"2023","journal-title":"arXiv preprint arXiv:2306.00978"},{"key":"ref32","article-title":"Rptq: Reorder-based post-training quantization for large language models","author":"Yuan","year":"2023","journal-title":"arXiv preprint arXiv:2304.01089"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3248282"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.2981056"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CAHPC.2018.8645906"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2017.30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00033"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2023.3332293"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00075"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/dac18074.2021.9586116"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00052"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1950.tb00463.x"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3458336.3465297"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10136985"},{"key":"ref45","article-title":"Approxabft: Approximate algorithm-based fault tolerance for vision transformers","author":"Xue","year":"2023","journal-title":"arXiv preprint arXiv:2302.10469"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tcsii.2021.3094923"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(84)90098-0"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1144"},{"key":"ref49","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv preprint arXiv:1609.07843"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1121\/1.2016299"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1206"},{"key":"ref52","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref53","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint arXiv:2110.14168"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11132610.pdf?arnumber=11132610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:47:51Z","timestamp":1762454871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132610\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11132610","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}