{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:37:07Z","timestamp":1781887027889,"version":"3.54.5"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T00:00:00Z","timestamp":1748131200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T00:00:00Z","timestamp":1748131200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010450","name":"Nova","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010450","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,25]]},"DOI":"10.1109\/iscas56072.2025.11043993","type":"proceedings-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T17:42:19Z","timestamp":1751046139000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["An Integer-only Quantization Framework for Edge Deployment of Large Language Models"],"prefix":"10.1109","author":[{"given":"Yaqi","family":"Hu","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuqing","family":"Yuan","sequence":"additional","affiliation":[{"name":"Pi2star Technology Ltd.,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weichen","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongpan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","first-page":"38 087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao"},{"key":"ref3","first-page":"17 402","article-title":"Outlier suppression: Pushing the limit of low-bit transformer language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.102"},{"key":"ref5","article-title":"Omniquant: Omnidirectionally calibrated quantization for large language models","author":"Shao","year":"2023"},{"key":"ref6","article-title":"Aweq: Post-training quantization with activation-weight equalization for large language models","author":"Li","year":"2023"},{"key":"ref7","article-title":"Rptq: Reorder-based post-training quantization for large language models","author":"Yuan","year":"2023"},{"key":"ref8","article-title":"Qllm: Accurate and efficient low-bitwidth quantization for large language models","author":"Liu","year":"2023"},{"key":"ref9","article-title":"Rethinking channel dimensions to isolate outliers for low-bit weight quantization of large language models","author":"Heo","year":"2023"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530504"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3126685"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46769.2022.9830277"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"ref16","first-page":"5506","article-title":"I-bert: Integer-only bert quantization","volume-title":"International conference on machine learning","author":"Kim"},{"key":"ref17","article-title":"Packqvit: Faster sub-8-bit vision transformers via full and packed quantization on the mobile","volume":"36","author":"Dong","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref19","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075835"},{"issue":"140","key":"ref21","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref22","first-page":"27 168","article-title":"Zeroquant: Efficient and affordable post-training quantization for large-scale transformers","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"London, United Kingdom","start":{"date-parts":[[2025,5,25]]},"end":{"date-parts":[[2025,5,28]]}},"container-title":["2025 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11043142\/11042930\/11043993.pdf?arnumber=11043993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T06:46:51Z","timestamp":1751093211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11043993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,25]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iscas56072.2025.11043993","relation":{},"subject":[],"published":{"date-parts":[[2025,5,25]]}}}