{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:44:35Z","timestamp":1772725475766,"version":"3.50.1"},"reference-count":24,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11132883","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":["3D-TokSIM: Stacking 3D Memory with Token-Stationary Compute-in-Memory for Speculative LLM Inference"],"prefix":"10.1109","author":[{"given":"Wentao","family":"Zhao","sequence":"first","affiliation":[{"name":"Peking University,Beijing,China"}]},{"given":"Boya","family":"Lv","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}]},{"given":"Meng","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}]},{"given":"Peiyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Nano Core Chip Electronic Technology,Hangzhou,China"}]},{"given":"Fengyun","family":"Yan","sequence":"additional","affiliation":[{"name":"Nano Core Chip Electronic Technology,Hangzhou,China"}]},{"given":"Yufei","family":"Ma","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}]},{"given":"Tianyu","family":"Jia","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}]},{"given":"Ru","family":"Huang","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}]},{"given":"Le","family":"Ye","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"H. T","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS59251.2023.10254711"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00078"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.456"},{"key":"ref5","article-title":"Powerinfer-2: Fast large language model inference on a smartphone","author":"Xue","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM13553.2020.9372039"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731694"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310258"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/VLSITechnologyandCir57934.2023.10185427"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3657375"},{"key":"ref12","article-title":"SK hynix is now shipping its 24GB LPDDR5X DRAM, will debut on OnePlus Ace 2 Pro","author":"Michail","year":"2023"},{"key":"ref13","article-title":"Fast inference from transformers via speculative decoding","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ICML\u201923","author":"Leviathan"},{"key":"ref14","article-title":"Predictive pipelined decoding: A compute-latency trade-off for exact llm decoding","volume":"abs\/2307.05908","author":"Yang","year":"2023","journal-title":"ArXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.88"},{"key":"ref16","article-title":"Inference with reference: Lossless acceleration of large language models","volume-title":"Tech. Rep. MSR-TR-2023-17","author":"Yang","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656219"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref19","volume-title":"baidu-research\/tensorflow-allreduce","author":"Baidu","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42614.2022.9731645"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2939682"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247855"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"ref24","first-page":"4396","article-title":"Quip: 2-bit quantization of large language models with guarantees","volume":"36","author":"Chee","year":"2023","journal-title":"Advances in neural information processing systems"}],"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\/11132883.pdf?arnumber=11132883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:56:16Z","timestamp":1758002176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11132883","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}