{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:52:06Z","timestamp":1776783126346,"version":"3.51.2"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,22]]},"DOI":"10.1109\/aicas59952.2024.10595874","type":"proceedings-article","created":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T17:30:48Z","timestamp":1721410248000},"page":"497-501","source":"Crossref","is-referenced-by-count":3,"title":["Real Post-Training Quantization Framework for Resource-Optimized Multiplier in LLMs"],"prefix":"10.1109","author":[{"given":"Minseok","family":"Seo","sequence":"first","affiliation":[{"name":"Inter-University Semiconductor Research Center (ISRC), Seoul National University,Department of Electrical and Computer Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seongho","family":"Jeong","sequence":"additional","affiliation":[{"name":"Inter-University Semiconductor Research Center (ISRC), Seoul National University,Department of Electrical and Computer Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyuk-Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"Inter-University Semiconductor Research Center (ISRC), Seoul National University,Department of Electrical and Computer Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan Truong","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Inter-University Semiconductor Research Center (ISRC), Seoul National University,Department of Electrical and Computer Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401655"},{"key":"ref2","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":"ref3","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"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"ref5","article-title":"Fighting quantization bias with bias","author":"Finkelstein","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2016.7539146"},{"key":"ref8","article-title":"Squeezellm: Dense-and-sparse quantization","author":"Kim","year":"2023"},{"key":"ref9","article-title":"Full stack optimization of transformer inference: a survey","author":"Kim","year":"2023"},{"key":"ref10","article-title":"FP8 quantization: The power of the exponent","volume-title":"Advances in Neural Information Processing Systems","author":"Kuzmin","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643569"},{"key":"ref12","first-page":"4486","article-title":"Same, same but different: Recovering neural network quantization error through weight factorization","volume-title":"International Conference on Machine Learning","author":"Meller"},{"key":"ref13","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1144"},{"key":"ref15","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/149"},{"key":"ref18","article-title":"Hybrid 8-bit floating point (hfp8) training and inference for deep neural networks","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Sun","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","article-title":"Huggingface\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019"},{"key":"ref21","article-title":"A survey on model compression for large language models","author":"Zhu","year":"2023"}],"event":{"name":"2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,4,22]]},"end":{"date-parts":[[2024,4,25]]}},"container-title":["2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10595550\/10595552\/10595874.pdf?arnumber=10595874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:34:24Z","timestamp":1750268064000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10595874\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,22]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/aicas59952.2024.10595874","relation":{},"subject":[],"published":{"date-parts":[[2024,4,22]]}}}