{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T05:10:22Z","timestamp":1756357822161,"version":"3.44.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,6]]},"DOI":"10.1109\/isvlsi65124.2025.11130222","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T18:20:15Z","timestamp":1756318815000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["CIM for Transformer Models: Enhancing Large Language Model Inference Efficiency"],"prefix":"10.1109","author":[{"given":"Meng-Syuan","family":"Li","sequence":"first","affiliation":[{"name":"National Central University,Department of Electrical Engineering,Taoyuan,Taiwan"}]},{"given":"Jung-Fang","family":"Ke","sequence":"additional","affiliation":[{"name":"National Central University,Department of Electrical Engineering,Taoyuan,Taiwan"}]},{"given":"En-Ming","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science,Taipei,Taiwan"}]},{"given":"Zhi-Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"National Central University,Department of Electrical Engineering,Taoyuan,Taiwan"}]},{"given":"Yu-Guang","family":"Chen","sequence":"additional","affiliation":[{"name":"National Central University,Department of Electrical Engineering,Taoyuan,Taiwan"}]},{"given":"Chun-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science,Taipei,Taiwan"}]}],"member":"263","reference":[{"article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. Int. Conf. on Machine Learning (ICML)","author":"Sheng","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"article-title":"MLC-LLM","year":"2023","author":"team","key":"ref3"},{"key":"ref4","article-title":"Opt: Open pre-trained transformer language models","volume":"abs\/2205.01068","author":"Zhang","year":"2022","journal-title":"ArXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001140"},{"key":"ref8","first-page":"10971105","article-title":"Imagenet classification with deep convolutional neural networks","volume":"2012","author":"Krizhevsky","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178781"},{"key":"ref11","article-title":"Faster R-CNN: Towards realtime object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. on Machine Learning (ICML)","author":"Xiao","key":"ref12"},{"key":"ref13","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 (NeurIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1186\/s11671-020-03299-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ted.2018.2849872"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IRPS46558.2021.9405092"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643444"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1088\/0957-4484\/24\/38\/382001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2967069"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2790840"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.201900082"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42614.2022.9731725"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46769.2022.9830490"},{"key":"ref25","first-page":"485","article-title":"An rram-based computing-in-memory architecture and its application in accelerating transformer inference","author":"Zhaojun","year":"2023","journal-title":"IEEE Trans. on Very Large Scale Integration (VLSI) Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415640"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2012.2185930"},{"article-title":"Wrap: Weight remapping and processing in rram-based neural network accelerators considering thermal effect","volume-title":"Design, Automation and Test in Europe Conf. (DATE)","author":"Po-Yuan","key":"ref28"}],"event":{"name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","start":{"date-parts":[[2025,7,6]]},"location":"Kalamata, Greece","end":{"date-parts":[[2025,7,9]]}},"container-title":["2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11129697\/11130193\/11130222.pdf?arnumber=11130222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:31:12Z","timestamp":1756355472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130222\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/isvlsi65124.2025.11130222","relation":{},"subject":[],"published":{"date-parts":[[2025,7,6]]}}}