{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:00:27Z","timestamp":1780639227352,"version":"3.54.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"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":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539190","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Fast and Energy-Efficient Support for Low-Precision LLMs on PIM"],"prefix":"10.23919","author":[{"given":"Byeori","family":"Kim","sequence":"first","affiliation":[{"name":"Pohang University of Science and Technology (POSTECH),Department of Computer Science and Engineering,Pohang,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sangjun","family":"Lee","sequence":"additional","affiliation":[{"name":"Pohang University of Science and Technology (POSTECH),Graduate School of Artificial Intelligence,Pohang,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eunhyeok","family":"Park","sequence":"additional","affiliation":[{"name":"Pohang University of Science and Technology (POSTECH),Graduate School of Artificial Intelligence,Pohang,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2857044"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HCS52781.2021.9567191"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895629"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651324"},{"key":"ref9","article-title":"OPTQ: Accurate quantization for generative pre-trained transformers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Frantar"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29237"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/lca.2025.3532682"},{"key":"ref13","first-page":"13 823","article-title":"QEFT: Quantization for efficient fine-tuning of LLMs","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","author":"Lee"},{"key":"ref14","first-page":"35 520","article-title":"AMQ: Enabling AutoML for mixed-precision weight-only quantization of large language models","volume-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","author":"Lee"},{"key":"ref15","article-title":"Omniquant: Omnidirectionally calibrated quantization for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shao"},{"key":"ref16","article-title":"PB-LLM: Partially binarized large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yuan"},{"key":"ref17","article-title":"Quarot: outlier-free 4-bit inference in rotated llms","volume-title":"Proceedings of the 38th International Conference on Neural Information Processing Systems","author":"Ashkboos"},{"key":"ref18","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021"},{"key":"ref19","first-page":"132","article-title":"LLMC: Benchmarking large language model quantization with a versatile compression toolkit","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track","author":"Gong"},{"key":"ref20","article-title":"Pointer sentinel mixture models","volume-title":"International Conference on Learning Representations","author":"Merity"},{"issue":"1","key":"ref21","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"ref22","first-page":"1105","article-title":"Openroad: Toward a self-driving, open-source digital layout implementation tool chain","volume-title":"Proc. GOMACTECH","author":"Ajayi"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3085572"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/lca.2020.2973991"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2011.4"}],"event":{"name":"2026 Design, Automation & Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539190.pdf?arnumber=11539190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:07:13Z","timestamp":1780636033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":25,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539190","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}