{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:27:13Z","timestamp":1774538833162,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"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","award":["62272026,62104014"],"award-info":[{"award-number":["62272026,62104014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.23919\/date64628.2025.10993129","type":"proceedings-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:36:35Z","timestamp":1747848995000},"page":"1-7","source":"Crossref","is-referenced-by-count":3,"title":["FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs"],"prefix":"10.23919","author":[{"given":"Xilong","family":"Xie","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University,Beijing,China,100191"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University,Beijing,China,100191"}]},{"given":"Limin","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University,Beijing,China,100191"}]},{"given":"Meng","family":"Han","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University,Beijing,China,100191"}]},{"given":"Lin","family":"Sun","sequence":"additional","affiliation":[{"name":"Jiangsu Shuguang Optoelectric Co., Ltd"}]},{"given":"Shuai","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University,Beijing,China,100191"}]},{"given":"Xiangrong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University,Beijing,China,100191"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Hardware-aware parallel prompt decoding for memory-efficient acceleration of llm inference","author":"Luk","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","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"},{"key":"ref6","article-title":"Llm. int8 (): 8-bit matrix multiplication for transformers at scale","author":"Dettmers","year":"2022","journal-title":"corr abs\/2208.07339"},{"key":"ref7","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","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29237"},{"key":"ref9","article-title":"Llm-mq: Mixed-precision quantization for efficient llm deployment","volume-title":"The Efficient Natural Language and Speech Processing Workshop with NeurIPS","volume":"9","author":"Li","year":"2023"},{"key":"ref10","article-title":"Pb-llm: Partially binarized large language models","author":"Shang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"7197","article-title":"Up or down? adaptive rounding for post-training quantization","volume-title":"International Conference on Machine Learning","author":"Nagel","year":"2020"},{"key":"ref12","article-title":"Mobile and edge evaluation of large language models","volume-title":"Workshop on Efficient Systems for Foundation Models II@ ICML2024","author":"Laskaridis"},{"key":"ref13","article-title":"Outlier suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","author":"Wei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658498"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527401"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04052-8"},{"key":"ref18","first-page":"160","article-title":"Abstractive long text summarization using large language models","volume":"12","author":"Keswani","year":"2024","journal-title":"Int. J. Intell. Syst. Appl. Eng"},{"key":"ref19","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Squeezellm: Dense-and-sparse quantization","author":"Kim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00080"},{"key":"ref23","first-page":"30 318","article-title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"ref25","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv preprint"},{"issue":"140","key":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2370-0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS.2016.7841286"}],"event":{"name":"2025 Design, Automation & Test in Europe Conference (DATE)","location":"Lyon, France","start":{"date-parts":[[2025,3,31]]},"end":{"date-parts":[[2025,4,2]]}},"container-title":["2025 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10992638\/10992588\/10993129.pdf?arnumber=10993129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:33:07Z","timestamp":1747891987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10993129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":28,"URL":"https:\/\/doi.org\/10.23919\/date64628.2025.10993129","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}