{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T04:05:28Z","timestamp":1747973128635,"version":"3.41.0"},"reference-count":31,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.23919\/date64628.2025.10993224","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":0,"title":["Leveraging Compute-in-Memory for Efficient Generative Model Inference in TPUs"],"prefix":"10.23919","author":[{"given":"Zhantong","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, Peking University,Beijing,China"}]},{"given":"Hongou","family":"Li","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University,Beijing,China"}]},{"given":"Wenjie","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University,Beijing,China"}]},{"given":"Meng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University,Beijing,China"}]},{"given":"Le","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University,Beijing,China"}]},{"given":"Ru","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University,Beijing,China"}]},{"given":"Tianyu","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University,Beijing,China"}]}],"member":"263","reference":[{"article-title":"Introducing ChatGPT","volume-title":"OpenAI","year":"2022","key":"ref1"},{"volume-title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","year":"2024","author":"Esser","key":"ref2"},{"journal-title":"Open-Sora: Democratizing Efficient Video Production for All","year":"2024","author":"Zheng","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/isca52012.2021.00010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662392"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062985"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731762"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067779"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454395"},{"journal-title":"LLM Inference Unveiled: Survey and Roofline Model Insights","year":"2024","author":"Yuan","key":"ref12"},{"journal-title":"A Survey of Large Language Models","year":"2023","author":"Zhao","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"journal-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","year":"2023","author":"Touvron","key":"ref16"},{"volume-title":"Stanford Alpaca: An Instruction-following LLaMA model","year":"2023","author":"Taori","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062953"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2021.3092533"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067260"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ESSERC62670.2024.10719471"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00082"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS61541.2024.00012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067555"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00016"},{"journal-title":"Online normalizer calculation for softmax","year":"2018","author":"Milakov","key":"ref27"},{"journal-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","year":"2020","author":"Shoeybi","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"ref30","article-title":"Language Models are Few-Shot Learners","volume":"abs\/2005.14165","author":"Brown","year":"2020","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3251696"}],"event":{"name":"2025 Design, Automation & Test in Europe Conference (DATE)","start":{"date-parts":[[2025,3,31]]},"location":"Lyon, France","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\/10993224.pdf?arnumber=10993224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:57:04Z","timestamp":1747893424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10993224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":31,"URL":"https:\/\/doi.org\/10.23919\/date64628.2025.10993224","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}