{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T22:42:40Z","timestamp":1774219360392,"version":"3.50.1"},"reference-count":28,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007219","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\/dac63849.2025.11132980","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":["PISA: Efficient Precision-Slice Framework for LLMs with Adaptive Numerical Type"],"prefix":"10.1109","author":[{"given":"Ning","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Zongwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Qingxiao","family":"Sun","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing"}]},{"given":"Liqiang","family":"Lu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Fangxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint arXiv:2005.14165"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530660"},{"key":"ref4","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv preprint arXiv:2210.17323"},{"key":"ref5","article-title":"Combining multiple post-training techniques to achieve most efficient quantized 1 lms","author":"Sharify","year":"2024","journal-title":"arXiv preprint arXiv:2405.07135"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00523"},{"key":"ref8","article-title":"Gptvq: The blessing of dimensionality for 1lm quantization","author":"van Baalen","year":"2024","journal-title":"arXiv preprint arXiv:2402.15319"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00063"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3063265"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00082"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3655896"},{"key":"ref15","first-page":"17402","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":"ref16","first-page":"27-168","article-title":"Zeroquant: Efficient and affordable post-training quantization for largescale transformers","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"Qserve: W4a8kv4 quantization and system co-design for efficient llm serving","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv:2405.04532"},{"key":"ref18","article-title":"Fp.6\u20131lm: Efficiently serving large language models through fp.6-centric algorithm-system co-design","author":"Xia","year":"2024","journal-title":"arXiv preprint arXiv:2401.14112"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCASAI.2024.3491941"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASC.2015.2507125"},{"key":"ref21","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2205.01068"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref24","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv preprint arXiv:1609.07843"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173171"},{"issue":"2","key":"ref27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3085572","article-title":"Cacti 7: New tools for interconnect exploration in innovative off-chip memories","volume":"14","author":"Balasubramonian","year":"2017","journal-title":"ACM Transactions on Architecture and Code Optimization (TACO)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00095"}],"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\/11132980.pdf?arnumber=11132980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:24:47Z","timestamp":1758000287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132980\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11132980","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}