{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:01:35Z","timestamp":1776931295863,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":92,"publisher":"ACM","funder":[{"name":"PRISM, a center in JUMP 2.0, an SRC program sponsored by DARPA"},{"name":"CoCoSys, a center in JUMP 2.0, an SRC program sponsored by DARPA.","award":[""],"award-info":[{"award-number":[""]}]},{"name":"NSF CCF-2112665 (TILOS AI Research Institute)","award":["2112665"],"award-info":[{"award-number":["2112665"]}]},{"name":"Collaborative Research: MLWiNS: Hyperdimensional Computing for Scalable IoT Intelligence","award":["2003279"],"award-info":[{"award-number":["2003279"]}]},{"name":"CCRI: ENS: Cognitive Hardware and Software Ecosystem Community Infrastructure","award":["2120019"],"award-info":[{"award-number":["2120019"]}]},{"name":"Collaborative Research: IIS: RI: Medium: Lifelong learning with hyper dimensional computing","award":["2211386"],"award-info":[{"award-number":["2211386"]}]},{"name":"Category II: A Prototype National Research Platform","award":["2112167"],"award-info":[{"award-number":["2112167"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756043","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:21:19Z","timestamp":1760721679000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6358-0394","authenticated-orcid":false,"given":"Yue","family":"Pan","sequence":"first","affiliation":[{"name":"University of California, San Diego, La Jolla, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5409-321X","authenticated-orcid":false,"given":"Zihan","family":"Xia","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7518-9472","authenticated-orcid":false,"given":"Po-Kai","family":"Hsu","sequence":"additional","affiliation":[{"name":"Georgia Tech, Atlanta, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0641-3677","authenticated-orcid":false,"given":"Lanxiang","family":"Hu","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1157-0127","authenticated-orcid":false,"given":"Hyungyo","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Illinois, Urbana-Champaign, Urbana, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1438-2439","authenticated-orcid":false,"given":"Janak","family":"Sharda","sequence":"additional","affiliation":[{"name":"Georgia Tech, Atlanta, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5523-7270","authenticated-orcid":false,"given":"Minxuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5700-8846","authenticated-orcid":false,"given":"Nam Sung","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Illinois, Urbana-Champaign, Urbana, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0068-3652","authenticated-orcid":false,"given":"Shimeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Georgia Tech, Atlanta, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6954-997X","authenticated-orcid":false,"given":"Tajana","family":"Rosing","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8104-5136","authenticated-orcid":false,"given":"Mingu","family":"Kang","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"2019. IEEE Standard for Floating-Point Arithmetic. IEEE Std 754-2019 (Revision of IEEE 754-2008) (2019) 1\u201384. 10.1109\/IEEESTD.2019.8766229","DOI":"10.1109\/IEEESTD.2019.8766229"},{"key":"e_1_3_3_1_3_2","volume-title":"DDR5 SDRAM Standard","year":"2020","unstructured":"2020. DDR5 SDRAM Standard. JEDEC Standard JESD79-5. JEDEC Solid State Technology Association. https:\/\/www.jedec.org\/standards-documents\/docs\/jesd79-5."},{"key":"e_1_3_3_1_4_2","volume-title":"Chatbot arena: An open platform for evaluating llms by human preference","year":"2024","unstructured":"2024. Chatbot arena: An open platform for evaluating llms by human preference."},{"key":"e_1_3_3_1_5_2","unstructured":"Meta AI. 2025. The llama 4 herd: The beginning of a new era of natively multimodal AI Innovation. https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/"},{"key":"e_1_3_3_1_6_2","unstructured":"AtlasUnified. 2023. Atlas-Converse Dataset. https:\/\/huggingface.co\/datasets\/AtlasUnified\/atlas-converse."},{"key":"e_1_3_3_1_7_2","unstructured":"AtlasUnified. 2025. Atlas-Reasoning Dataset. https:\/\/huggingface.co\/datasets\/AtlasUnified\/Atlas-Reasoning. Accessed: 2025-04-10."},{"key":"e_1_3_3_1_8_2","unstructured":"Cadence. 2024. Genus Synthesis Solution. https:\/\/www.cadence.com\/en_US\/home\/tools\/digital-design-and-signoff\/synthesis\/genus-synthesis-solution.html Accessed: 2024-12-18."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870333"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM13553.2020.9371905"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM45741.2023.10413828"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM45625.2022.10019464"},{"key":"e_1_3_3_1_13_2","unstructured":"Wei-Lin Chiang Lianmin Zheng Ying Sheng Anastasios\u00a0Nikolas Angelopoulos Tianle Li Dacheng Li Hao Zhang Banghua Zhu Michael Jordan Joseph\u00a0E. Gonzalez and Ion Stoica. 2024. Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference. arxiv:https:\/\/arXiv.org\/abs\/2403.04132\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2403.04132"},{"key":"e_1_3_3_1_14_2","unstructured":"Rewon Child Scott Gray Alec Radford and Ilya Sutskever. 2019. Generating long sequences with sparse transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1904.10509 (2019)."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454327"},{"key":"e_1_3_3_1_16_2","first-page":"1","volume-title":"2024 IEEE Asian Solid-State Circuits Conference (A-SSCC)","author":"Choi Jaewoong","year":"2024","unstructured":"Jaewoong Choi, Yi-Gyeong Kim, Juyeob Kim, Jaehoon Chung, Young-Deuk Jeon, Min-Hyung Cho, Sujin Park, and Jinho Han. 2024. A 6.4 Gb\/s\/pin HBM3 Digital PHY with Low-Power, Area-Efficient Techniques for Chiplet-Based AI processors in 12-nm CMOS. In 2024 IEEE Asian Solid-State Circuits Conference (A-SSCC). IEEE, 1\u20133."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46783.2024.10631471"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Jack Choquette. 2023. NVIDIA Hopper H100 GPU: Scaling Performance. IEEE Micro 43 3 (2023) 9\u201317. 10.1109\/MM.2023.3256796","DOI":"10.1109\/MM.2023.3256796"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Jack Choquette Wishwesh Gandhi Olivier Giroux Nick Stam and Ronny Krashinsky. 2021. NVIDIA A100 Tensor Core GPU: Performance and Innovation. IEEE Micro 41 2 (2021) 29\u201335. 10.1109\/MM.2021.3061394","DOI":"10.1109\/MM.2021.3061394"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Lawrence\u00a0T Clark Vinay Vashishtha Lucian Shifren Aditya Gujja Saurabh Sinha Brian Cline Chandarasekaran Ramamurthy and Greg Yeric. 2016. ASAP7: A 7-nm finFET predictive process design kit. Microelectronics Journal 53 (2016) 105\u2013115.","DOI":"10.1016\/j.mejo.2016.04.006"},{"key":"e_1_3_3_1_21_2","unstructured":"Peter Clark Isaac Cowhey Oren Etzioni Tushar Khot Ashish Sabharwal Carissa Schoenick and Oyvind Tafjord. 2018. Think you have Solved Question Answering? Try ARC the AI2 Reasoning Challenge. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1803.05457 (2018). https:\/\/arxiv.org\/abs\/1803.05457"},{"key":"e_1_3_3_1_22_2","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.14168 (2021)."},{"key":"e_1_3_3_1_23_2","volume-title":"Scaling to 1,000\u2011Layer 3D NAND in the AI Era","author":"Research Counterpoint","year":"2024","unstructured":"Counterpoint Research and Lam Research. 2024. Scaling to 1,000\u2011Layer 3D NAND in the AI Era. White paper. Counterpoint Research (in partnership with Lam Research). https:\/\/filecache.mediaroom.com\/mr5mr_lamresearch\/182770\/Counterpoint_Research_Paper_Scaling_to_1000-Layer_3D_NAND_in_the_AI_Era.pdf 17 pp.."},{"key":"e_1_3_3_1_24_2","unstructured":"Coventor. [n. d.]. Coventor Semulator3D. https:\/\/www.coventor.com\/products\/semulator3d\/. Accessed: 2024-07-24."},{"key":"e_1_3_3_1_25_2","unstructured":"Damai Dai Chengqi Deng Chenggang Zhao RX Xu Huazuo Gao Deli Chen Jiashi Li Wangding Zeng Xingkai Yu Yu Wu et\u00a0al. 2024. Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.06066 (2024)."},{"key":"e_1_3_3_1_26_2","unstructured":"Databricks. 2024. DBRX: A New State-of-the-Art Open LLM. Databricks Blog (2024). https:\/\/www.databricks.com\/blog\/introducing-dbrx-new-state-art-open-llm"},{"key":"e_1_3_3_1_27_2","unstructured":"DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2501.12948\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_3_1_28_2","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai Daya Guo Dejian Yang Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fucong Dai Fuli Luo Guangbo Hao Guanting Chen Guowei Li H. Zhang Han Bao Hanwei Xu Haocheng Wang Haowei Zhang Honghui Ding Huajian Xin Huazuo Gao Hui Li Hui Qu J.\u00a0L. Cai Jian Liang Jianzhong Guo Jiaqi Ni Jiashi Li Jiawei Wang Jin Chen Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li Junxiao Song Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Lei Xu Leyi Xia Liang Zhao Litong Wang Liyue Zhang Meng Li Miaojun Wang Mingchuan Zhang Minghua Zhang Minghui Tang Mingming Li Ning Tian Panpan Huang Peiyi Wang Peng Zhang Qiancheng Wang Qihao Zhu Qinyu Chen Qiushi Du R.\u00a0J. Chen R.\u00a0L. Jin Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang Runxin Xu Ruoyu Zhang Ruyi Chen S.\u00a0S. Li Shanghao Lu Shangyan Zhou Shanhuang Chen Shaoqing Wu Shengfeng Ye Shengfeng Ye Shirong Ma Shiyu Wang Shuang Zhou Shuiping Yu Shunfeng Zhou Shuting Pan T. Wang Tao Yun Tian Pei Tianyu Sun W.\u00a0L. Xiao Wangding Zeng Wanjia Zhao Wei An Wen Liu Wenfeng Liang Wenjun Gao Wenqin Yu Wentao Zhang X.\u00a0Q. Li Xiangyue Jin Xianzu Wang Xiao Bi Xiaodong Liu Xiaohan Wang Xiaojin Shen Xiaokang Chen Xiaokang Zhang Xiaosha Chen Xiaotao Nie Xiaowen Sun Xiaoxiang Wang Xin Cheng Xin Liu Xin Xie Xingchao Liu Xingkai Yu Xinnan Song Xinxia Shan Xinyi Zhou Xinyu Yang Xinyuan Li Xuecheng Su Xuheng Lin Y.\u00a0K. Li Y.\u00a0Q. Wang Y.\u00a0X. Wei Y.\u00a0X. Zhu Yang Zhang Yanhong Xu Yanhong Xu Yanping Huang Yao Li Yao Zhao Yaofeng Sun Yaohui Li Yaohui Wang Yi Yu Yi Zheng Yichao Zhang Yifan Shi Yiliang Xiong Ying He Ying Tang Yishi Piao Yisong Wang Yixuan Tan Yiyang Ma Yiyuan Liu Yongqiang Guo Yu Wu Yuan Ou Yuchen Zhu Yuduan Wang Yue Gong Yuheng Zou Yujia He Yukun Zha Yunfan Xiong Yunxian Ma Yuting Yan Yuxiang Luo Yuxiang You Yuxuan Liu Yuyang Zhou Z.\u00a0F. Wu Z.\u00a0Z. Ren Zehui Ren Zhangli Sha Zhe Fu Zhean Xu Zhen Huang Zhen Zhang Zhenda Xie Zhengyan Zhang Zhewen Hao Zhibin Gou Zhicheng Ma Zhigang Yan Zhihong Shao Zhipeng Xu Zhiyu Wu Zhongyu Zhang Zhuoshu Li Zihui Gu Zijia Zhu Zijun Liu Zilin Li Ziwei Xie Ziyang Song Ziyi Gao and Zizheng Pan. 2025. DeepSeek-V3 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2412.19437\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_3_1_29_2","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171\u20134186."},{"key":"e_1_3_3_1_30_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929 (2020). arXiv:https:\/\/arXiv.org\/abs\/2010.11929https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_3_1_31_2","unstructured":"Nan Du Yanping Huang Andrew\u00a0M. Dai Simon Tong Dmitry Lepikhin Yuanzhong Xu Maxim Krikun Yanqi Zhou Adams\u00a0Wei Yu Orhan Firat Barret Zoph Liam Fedus Maarten Bosma Zongwei Zhou Tao Wang Yu\u00a0Emma Wang Kellie Webster Marie Pellat Kevin Robinson Kathleen Meier-Hellstern Toju Duke Lucas Dixon Kun Zhang Quoc\u00a0V Le Yonghui Wu Zhifeng Chen and Claire Cui. 2022. GLaM: Efficient Scaling of Language Models with Mixture-of-Experts. arxiv:https:\/\/arXiv.org\/abs\/2112.06905\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2112.06905"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Munonyedi Egbo. 2022. A review of the thermal performance of vapor chambers and heat sinks: Critical heat flux thermal resistances and surface temperatures. International Journal of Heat and Mass Transfer 183 (2022) 122108.","DOI":"10.1016\/j.ijheatmasstransfer.2021.122108"},{"key":"e_1_3_3_1_33_2","unstructured":"William Fedus Barret Zoph and Noam Shazeer. 2022. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. arxiv:https:\/\/arXiv.org\/abs\/2101.03961\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2101.03961"},{"key":"e_1_3_3_1_34_2","unstructured":"Seokjin Go and Divya Mahajan. 2025. MoETuner: Optimized Mixture of Expert Serving with Balanced Expert Placement and Token Routing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.06643 (2025)."},{"key":"e_1_3_3_1_35_2","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan Amy Yang Angela Fan Anirudh Goyal Anthony Hartshorn Aobo Yang Archi Mitra Archie Sravankumar Artem Korenev Arthur Hinsvark Arun Rao Aston Zhang Aurelien Rodriguez Austen Gregerson Ava Spataru Baptiste Roziere Bethany Biron Binh Tang Bobbie Chern Charlotte Caucheteux Chaya Nayak Chloe Bi Chris Marra Chris McConnell Christian Keller Christophe Touret Chunyang Wu Corinne Wong Cristian\u00a0Canton Ferrer Cyrus Nikolaidis Damien Allonsius Daniel Song Danielle Pintz Danny Livshits Danny Wyatt David Esiobu Dhruv Choudhary Dhruv Mahajan Diego Garcia-Olano Diego Perino Dieuwke Hupkes Egor Lakomkin Ehab AlBadawy Elina Lobanova Emily Dinan Eric\u00a0Michael Smith Filip Radenovic Francisco Guzm\u00e1n Frank Zhang Gabriel Synnaeve Gabrielle Lee Georgia\u00a0Lewis Anderson Govind Thattai Graeme Nail Gregoire Mialon Guan Pang Guillem Cucurell Hailey Nguyen Hannah Korevaar Hu Xu Hugo Touvron Iliyan Zarov Imanol\u00a0Arrieta Ibarra Isabel Kloumann Ishan Misra Ivan Evtimov Jack Zhang Jade Copet Jaewon Lee Jan Geffert Jana Vranes Jason Park Jay Mahadeokar Jeet Shah Jelmer van\u00a0der Linde Jennifer Billock Jenny Hong Jenya Lee Jeremy Fu Jianfeng Chi Jianyu Huang Jiawen Liu Jie Wang Jiecao Yu Joanna Bitton Joe Spisak Jongsoo Park Joseph Rocca Joshua Johnstun Joshua Saxe Junteng Jia Kalyan\u00a0Vasuden Alwala Karthik Prasad Kartikeya Upasani Kate Plawiak Ke Li Kenneth Heafield Kevin Stone Khalid El-Arini Krithika Iyer Kshitiz Malik Kuenley Chiu Kunal Bhalla Kushal Lakhotia Lauren Rantala-Yeary Laurens van\u00a0der Maaten Lawrence Chen Liang Tan Liz Jenkins Louis Martin Lovish Madaan Lubo Malo Lukas Blecher Lukas Landzaat Luke de Oliveira Madeline Muzzi Mahesh Pasupuleti Mannat Singh Manohar Paluri Marcin Kardas Maria Tsimpoukelli Mathew Oldham Mathieu Rita Maya Pavlova Melanie Kambadur Mike Lewis Min Si Mitesh\u00a0Kumar Singh Mona Hassan Naman Goyal Narjes Torabi Nikolay Bashlykov Nikolay Bogoychev Niladri Chatterji Ning Zhang Olivier Duchenne Onur \u00c7elebi Patrick Alrassy Pengchuan Zhang Pengwei Li Petar Vasic Peter Weng Prajjwal Bhargava Pratik Dubal Praveen Krishnan Punit\u00a0Singh Koura Puxin Xu Qing He Qingxiao Dong Ragavan Srinivasan Raj Ganapathy Ramon Calderer Ricardo\u00a0Silveira Cabral Robert Stojnic Roberta Raileanu Rohan Maheswari Rohit Girdhar Rohit Patel Romain Sauvestre Ronnie Polidoro Roshan Sumbaly Ross Taylor Ruan Silva Rui Hou Rui Wang Saghar Hosseini Sahana Chennabasappa Sanjay Singh Sean Bell Seohyun\u00a0Sonia Kim Sergey Edunov Shaoliang Nie Sharan Narang Sharath Raparthy Sheng Shen Shengye Wan Shruti Bhosale Shun Zhang Simon Vandenhende Soumya Batra Spencer Whitman Sten Sootla Stephane Collot Suchin Gururangan Sydney Borodinsky Tamar Herman Tara Fowler Tarek Sheasha Thomas Georgiou Thomas Scialom Tobias Speckbacher Todor Mihaylov Tong Xiao Ujjwal Karn Vedanuj Goswami Vibhor Gupta Vignesh Ramanathan Viktor Kerkez Vincent Gonguet Virginie Do Vish Vogeti V\u00edtor Albiero Vladan Petrovic Weiwei Chu Wenhan Xiong Wenyin Fu Whitney Meers Xavier Martinet Xiaodong Wang Xiaofang Wang Xiaoqing\u00a0Ellen Tan Xide Xia Xinfeng Xie Xuchao Jia Xuewei Wang Yaelle Goldschlag Yashesh Gaur Yasmine Babaei Yi Wen Yiwen Song Yuchen Zhang Yue Li Yuning Mao Zacharie\u00a0Delpierre Coudert Zheng Yan Zhengxing Chen Zoe Papakipos Aaditya Singh Aayushi Srivastava Abha Jain Adam Kelsey Adam Shajnfeld Adithya Gangidi Adolfo Victoria Ahuva Goldstand Ajay Menon Ajay Sharma Alex Boesenberg Alexei Baevski Allie Feinstein Amanda Kallet Amit Sangani Amos Teo Anam Yunus Andrei Lupu Andres Alvarado Andrew Caples Andrew Gu Andrew Ho Andrew Poulton Andrew Ryan Ankit Ramchandani Annie Dong Annie Franco Anuj Goyal Aparajita Saraf Arkabandhu Chowdhury Ashley Gabriel Ashwin Bharambe Assaf Eisenman Azadeh Yazdan Beau James Ben Maurer Benjamin Leonhardi Bernie Huang Beth Loyd Beto\u00a0De Paola Bhargavi Paranjape Bing Liu Bo Wu Boyu Ni Braden Hancock Bram Wasti Brandon Spence Brani Stojkovic Brian Gamido Britt Montalvo Carl Parker Carly Burton Catalina Mejia Ce Liu Changhan Wang Changkyu Kim Chao Zhou Chester Hu Ching-Hsiang Chu Chris Cai Chris Tindal Christoph Feichtenhofer Cynthia Gao Damon Civin Dana Beaty Daniel Kreymer Daniel Li David Adkins David Xu Davide Testuggine Delia David Devi Parikh Diana Liskovich Didem Foss Dingkang Wang Duc Le Dustin Holland Edward Dowling Eissa Jamil Elaine Montgomery Eleonora Presani Emily Hahn Emily Wood Eric-Tuan Le Erik Brinkman Esteban Arcaute Evan Dunbar Evan Smothers Fei Sun Felix Kreuk Feng Tian Filippos Kokkinos Firat Ozgenel Francesco Caggioni Frank Kanayet Frank Seide Gabriela\u00a0Medina Florez Gabriella Schwarz Gada Badeer Georgia Swee Gil Halpern Grant Herman Grigory Sizov Guangyi Zhang Guna Lakshminarayanan Hakan Inan Hamid Shojanazeri Han Zou Hannah Wang Hanwen Zha Haroun Habeeb Harrison Rudolph Helen Suk Henry Aspegren Hunter Goldman Hongyuan Zhan Ibrahim Damlaj Igor Molybog Igor Tufanov Ilias Leontiadis Irina-Elena Veliche Itai Gat Jake Weissman James Geboski James Kohli Janice Lam Japhet Asher Jean-Baptiste Gaya Jeff Marcus Jeff Tang Jennifer Chan Jenny Zhen Jeremy Reizenstein Jeremy Teboul Jessica Zhong Jian Jin Jingyi Yang Joe Cummings Jon Carvill Jon Shepard Jonathan McPhie Jonathan Torres Josh Ginsburg Junjie Wang Kai Wu Kam\u00a0Hou U Karan Saxena Kartikay Khandelwal Katayoun Zand Kathy Matosich Kaushik Veeraraghavan Kelly Michelena Keqian Li Kiran Jagadeesh Kun Huang Kunal Chawla Kyle Huang Lailin Chen Lakshya Garg Lavender A Leandro Silva Lee Bell Lei Zhang Liangpeng Guo Licheng Yu Liron Moshkovich Luca Wehrstedt Madian Khabsa Manav Avalani Manish Bhatt Martynas Mankus Matan Hasson Matthew Lennie Matthias Reso Maxim Groshev Maxim Naumov Maya Lathi Meghan Keneally Miao Liu Michael\u00a0L. Seltzer Michal Valko Michelle Restrepo Mihir Patel Mik Vyatskov Mikayel Samvelyan Mike Clark Mike Macey Mike Wang Miquel\u00a0Jubert Hermoso Mo Metanat Mohammad Rastegari Munish Bansal Nandhini Santhanam Natascha Parks Natasha White Navyata Bawa Nayan Singhal Nick Egebo Nicolas Usunier Nikhil Mehta Nikolay\u00a0Pavlovich Laptev Ning Dong Norman Cheng Oleg Chernoguz Olivia Hart Omkar Salpekar Ozlem Kalinli Parkin Kent Parth Parekh Paul Saab Pavan Balaji Pedro Rittner Philip Bontrager Pierre Roux Piotr Dollar Polina Zvyagina Prashant Ratanchandani Pritish Yuvraj Qian Liang Rachad Alao Rachel Rodriguez Rafi Ayub Raghotham Murthy Raghu Nayani Rahul Mitra Rangaprabhu Parthasarathy Raymond Li Rebekkah Hogan Robin Battey Rocky Wang Russ Howes Ruty Rinott Sachin Mehta Sachin Siby Sai\u00a0Jayesh Bondu Samyak Datta Sara Chugh Sara Hunt Sargun Dhillon Sasha Sidorov Satadru Pan Saurabh Mahajan Saurabh Verma Seiji Yamamoto Sharadh Ramaswamy Shaun Lindsay Shaun Lindsay Sheng Feng Shenghao Lin Shengxin\u00a0Cindy Zha Shishir Patil Shiva Shankar Shuqiang Zhang Shuqiang Zhang Sinong Wang Sneha Agarwal Soji Sajuyigbe Soumith Chintala Stephanie Max Stephen Chen Steve Kehoe Steve Satterfield Sudarshan Govindaprasad Sumit Gupta Summer Deng Sungmin Cho Sunny Virk Suraj Subramanian Sy Choudhury Sydney Goldman Tal Remez Tamar Glaser Tamara Best Thilo Koehler Thomas Robinson Tianhe Li Tianjun Zhang Tim Matthews Timothy Chou Tzook Shaked Varun Vontimitta Victoria Ajayi Victoria Montanez Vijai Mohan Vinay\u00a0Satish Kumar Vishal Mangla Vlad Ionescu Vlad Poenaru Vlad\u00a0Tiberiu Mihailescu Vladimir Ivanov Wei Li Wenchen Wang Wenwen Jiang Wes Bouaziz Will Constable Xiaocheng Tang Xiaojian Wu Xiaolan Wang Xilun Wu Xinbo Gao Yaniv Kleinman Yanjun Chen Ye Hu Ye Jia Ye Qi Yenda Li Yilin Zhang Ying Zhang Yossi Adi Youngjin Nam Yu Wang Yu Zhao Yuchen Hao Yundi Qian Yunlu Li Yuzi He Zach Rait Zachary DeVito Zef Rosnbrick Zhaoduo Wen Zhenyu Yang Zhiwei Zhao and Zhiyu Ma. 2024. The Llama 3 Herd of Models. arxiv:https:\/\/arXiv.org\/abs\/2407.21783\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.23919\/VLSITechnologyandCir57934.2023.10185290"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISDCS52006.2021.9397913"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"e_1_3_3_1_40_2","unstructured":"Xin He Shunkang Zhang Yuxin Wang Haiyan Yin Zihao Zeng Shaohuai Shi Zhenheng Tang Xiaowen Chu Ivor Tsang and Ong\u00a0Yew Soon. 2024. Expertflow: Optimized expert activation and token allocation for efficient mixture-of-experts inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.17954 (2024)."},{"key":"e_1_3_3_1_41_2","first-page":"1727","volume-title":"Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency","author":"Henderson Peter","year":"2022","unstructured":"Peter Henderson, Andy Hu, David Romero, Mark Roberts, Daniel Chen, Emily Zhang, He He, Dan Jurafsky, Percy Liang, Nisan Stiennon, et\u00a0al. 2022. Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency. ACM, 1727\u20131742."},{"key":"e_1_3_3_1_42_2","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Dawn Song and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Understanding. Proceedings of the International Conference on Learning Representations (ICLR) (2021)."},{"key":"e_1_3_3_1_43_2","unstructured":"Dan Hendrycks Collin Burns Saurav Kadavath Akul Arora Steven Basart Eric Tang Dawn Song and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. NeurIPS (2021)."},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"e_1_3_3_1_45_2","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_1_46_2","volume-title":"New 1T1C and 3T0C Cells in the 3D X\u2011DRAM Family: Advancing 3D NAND\u2011like DRAM Technology Using IGZO","author":"Hsu Fu\u2011Chang","year":"2025","unstructured":"Fu\u2011Chang Hsu, Richard\u00a0J. Huang, Chia\u2011Haur Chang, Re\u2011Peng Tsay, Jui\u2011Hsin Chang, and I\u2011Wei Huang. 2025. New 1T1C and 3T0C Cells in the 3D X\u2011DRAM Family: Advancing 3D NAND\u2011like DRAM Technology Using IGZO. White paper. NEO Semiconductor. https:\/\/neosemic.com\/wp-content\/uploads\/2025\/05\/NEO-White-Paper-for-ITIC-and-3T0C_V18_clean.pdf Version 1.1."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","unstructured":"Po-Kai Hsu Janak Sharda Xiangjin Wu H.-S.\u00a0Philip Wong and Shimeng Yu. 2025. Monolithic 3D Stackable DRAM. IEEE Nanotechnology Magazine 19 2 (2025) 7\u201316. 10.1109\/MNANO.2025.3533815","DOI":"10.1109\/MNANO.2025.3533815"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM50854.2024.10873439"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/IMW56887.2023.10145931"},{"key":"e_1_3_3_1_50_2","unstructured":"Celsia Inc.2025. Heat Sink Design. https:\/\/celsiainc.com\/technology\/heat-sink-design\/ Accessed: 2025-02-24."},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895480"},{"key":"e_1_3_3_1_52_2","unstructured":"Albert\u00a0Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Emma\u00a0Bou Hanna Florian Bressand Gianna Lengyel Guillaume Bour Guillaume Lample L\u00e9lio\u00a0Renard Lavaud Lucile Saulnier Marie-Anne Lachaux Pierre Stock Sandeep Subramanian Sophia Yang Szymon Antoniak Teven\u00a0Le Scao Th\u00e9ophile Gervet Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William\u00a0El Sayed. 2024. Mixtral of Experts. arxiv:https:\/\/arXiv.org\/abs\/2401.04088\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.04088"},{"key":"e_1_3_3_1_53_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom\u00a0B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling Laws for Neural Language Models. arxiv:https:\/\/arXiv.org\/abs\/2001.08361\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_3_1_54_2","unstructured":"Yoon\u00a0Jo Kim Yogendra\u00a0K Joshi Andrei\u00a0G Fedorov Young-Joon Lee and Sung-Kyu Lim. 2010. Thermal characterization of interlayer microfluidic cooling of three-dimensional integrated circuits with nonuniform heat flux. (2010)."},{"key":"e_1_3_3_1_55_2","unstructured":"Jakub Krajewski Jan Ludziejewski Kamil Adamczewski Maciej Pi\u00f3ro Micha\u0142 Krutul Szymon Antoniak Kamil Ciebiera Krystian Kr\u00f3l Tomasz Odrzyg\u00f3\u017ad\u017a Piotr Sankowski Marek Cygan and Sebastian Jaszczur. 2024. Scaling Laws for Fine-Grained Mixture of Experts. arxiv:https:\/\/arXiv.org\/abs\/2402.07871\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2402.07871"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","unstructured":"Junmo Lee Anni Lu Wantong Li and Shimeng Yu. 2024. NeuroSim V1.4: Extending Technology Support for Digital Compute-in-Memory Toward 1nm Node. IEEE Transactions on Circuits and Systems I: Regular Papers 71 4 (2024) 1733\u20131744. 10.1109\/TCSI.2024.3362822","DOI":"10.1109\/TCSI.2024.3362822"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"e_1_3_3_1_59_2","first-page":"945","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Li Jiamin","year":"2023","unstructured":"Jiamin Li, Yimin Jiang, Yibo Zhu, Cong Wang, and Hong Xu. 2023. Accelerating distributed { MoE} training and inference with lina. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 945\u2013959."},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_3_1_61_2","unstructured":"Niklas Muennighoff Luca Soldaini Dirk Groeneveld Kyle Lo Jacob Morrison Sewon Min Weijia Shi Pete Walsh Oyvind Tafjord Nathan Lambert Yuling Gu Shane Arora Akshita Bhagia Dustin Schwenk David Wadden Alexander Wettig Binyuan Hui Tim Dettmers Douwe Kiela Ali Farhadi Noah\u00a0A. Smith Pang\u00a0Wei Koh Amanpreet Singh and Hannaneh Hajishirzi. 2024. OLMoE: Open Mixture-of-Experts Language Models. arxiv:https:\/\/arXiv.org\/abs\/2409.02060\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2409.02060"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"crossref","unstructured":"M Muneeshwaran Yun-Jin Lee and Chi-Chuan Wang. 2022. Performance improvement of heat sink with vapor chamber base and heat pipe. Applied Thermal Engineering 215 (2022) 118932.","DOI":"10.1016\/j.applthermaleng.2022.118932"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"crossref","unstructured":"Juan\u00a0P Murrieta-Cortes Luis\u00a0E Paniagua-Guerra C\u00a0Ulises Gonzalez-Valle Alexander\u00a0S Rattner and Bladimir Ramos-Alvarado. 2024. Liquid-cooled heat sink design methodology with technical and commercial viability considerations: Case study of a partially 3-D printed prototype. Applied Thermal Engineering 247 (2024) 122933.","DOI":"10.1016\/j.applthermaleng.2024.122933"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124545"},{"key":"e_1_3_3_1_65_2","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat Red Avila Igor Babuschkin Suchir Balaji Valerie Balcom Paul Baltescu Haiming Bao Mohammad Bavarian Jeff Belgum Irwan Bello Jake Berdine Gabriel Bernadett-Shapiro Christopher Berner Lenny Bogdonoff Oleg Boiko Madelaine Boyd Anna-Luisa Brakman Greg Brockman Tim Brooks Miles Brundage Kevin Button Trevor Cai Rosie Campbell Andrew Cann Brittany Carey Chelsea Carlson Rory Carmichael Brooke Chan Che Chang Fotis Chantzis Derek Chen Sully Chen Ruby Chen Jason Chen Mark Chen Ben Chess Chester Cho Casey Chu Hyung\u00a0Won Chung Dave Cummings Jeremiah Currier Yunxing Dai Cory Decareaux Thomas Degry Noah Deutsch Damien Deville Arka Dhar David Dohan Steve Dowling Sheila Dunning Adrien Ecoffet Atty Eleti Tyna Eloundou David Farhi Liam Fedus Niko Felix Sim\u00f3n\u00a0Posada Fishman Juston Forte Isabella Fulford Leo Gao Elie Georges Christian Gibson Vik Goel Tarun Gogineni Gabriel Goh Rapha Gontijo-Lopes Jonathan Gordon Morgan Grafstein Scott Gray Ryan Greene Joshua Gross Shixiang\u00a0Shane Gu Yufei Guo Chris Hallacy Jesse Han Jeff Harris Yuchen He Mike Heaton Johannes Heidecke Chris Hesse Alan Hickey Wade Hickey Peter Hoeschele Brandon Houghton Kenny Hsu Shengli Hu Xin Hu Joost Huizinga Shantanu Jain Shawn Jain Joanne Jang Angela Jiang Roger Jiang Haozhun Jin Denny Jin Shino Jomoto Billie Jonn Heewoo Jun Tomer Kaftan \u0141ukasz Kaiser Ali Kamali Ingmar Kanitscheider Nitish\u00a0Shirish Keskar Tabarak Khan Logan Kilpatrick Jong\u00a0Wook Kim Christina Kim Yongjik Kim Jan\u00a0Hendrik Kirchner Jamie Kiros Matt Knight Daniel Kokotajlo \u0141ukasz Kondraciuk Andrew Kondrich Aris Konstantinidis Kyle Kosic Gretchen Krueger Vishal Kuo Michael Lampe Ikai Lan Teddy Lee Jan Leike Jade Leung Daniel Levy Chak\u00a0Ming Li Rachel Lim Molly Lin Stephanie Lin Mateusz Litwin Theresa Lopez Ryan Lowe Patricia Lue Anna Makanju Kim Malfacini Sam Manning Todor Markov Yaniv Markovski Bianca Martin Katie Mayer Andrew Mayne Bob McGrew Scott\u00a0Mayer McKinney Christine McLeavey Paul McMillan Jake McNeil David Medina Aalok Mehta Jacob Menick Luke Metz Andrey Mishchenko Pamela Mishkin Vinnie Monaco Evan Morikawa Daniel Mossing Tong Mu Mira Murati Oleg Murk David M\u00e9ly Ashvin Nair Reiichiro Nakano Rajeev Nayak Arvind Neelakantan Richard Ngo Hyeonwoo Noh Long Ouyang Cullen O\u2019Keefe Jakub Pachocki Alex Paino Joe Palermo Ashley Pantuliano Giambattista Parascandolo Joel Parish Emy Parparita Alex Passos Mikhail Pavlov Andrew Peng Adam Perelman Filipe de Avila Belbute\u00a0Peres Michael Petrov Henrique\u00a0Ponde de Oliveira\u00a0Pinto Michael Pokorny Michelle Pokrass Vitchyr\u00a0H. Pong Tolly Powell Alethea Power Boris Power Elizabeth Proehl Raul Puri Alec Radford Jack Rae Aditya Ramesh Cameron Raymond Francis Real Kendra Rimbach Carl Ross Bob Rotsted Henri Roussez Nick Ryder Mario Saltarelli Ted Sanders Shibani Santurkar Girish Sastry Heather Schmidt David Schnurr John Schulman Daniel Selsam Kyla Sheppard Toki Sherbakov Jessica Shieh Sarah Shoker Pranav Shyam Szymon Sidor Eric Sigler Maddie Simens Jordan Sitkin Katarina Slama Ian Sohl Benjamin Sokolowsky Yang Song Natalie Staudacher Felipe\u00a0Petroski Such Natalie Summers Ilya Sutskever Jie Tang Nikolas Tezak Madeleine\u00a0B. Thompson Phil Tillet Amin Tootoonchian Elizabeth Tseng Preston Tuggle Nick Turley Jerry Tworek Juan Felipe\u00a0Cer\u00f3n Uribe Andrea Vallone Arun Vijayvergiya Chelsea Voss Carroll Wainwright Justin\u00a0Jay Wang Alvin Wang Ben Wang Jonathan Ward Jason Wei CJ Weinmann Akila Welihinda Peter Welinder Jiayi Weng Lilian Weng Matt Wiethoff Dave Willner Clemens Winter Samuel Wolrich Hannah Wong Lauren Workman Sherwin Wu Jeff Wu Michael Wu Kai Xiao Tao Xu Sarah Yoo Kevin Yu Qiming Yuan Wojciech Zaremba Rowan Zellers Chong Zhang Marvin Zhang Shengjia Zhao Tianhao Zheng Juntang Zhuang William Zhuk and Barret Zoph. 2024. GPT-4 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2303.08774\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_3_1_66_2","unstructured":"OpenPhi. 2025. Programming Books LLaMA Dataset. https:\/\/huggingface.co\/datasets\/open-phi\/programming_books_llama. Accessed: 2025-04-10."},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473968"},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731562"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","unstructured":"Naebeom Park Sungju Ryu Jaeha Kung and Jae-Joon Kim. 2021. High-throughput Near-Memory Processing on CNNs with 3D HBM-like Memory. ACM Trans. Des. Autom. Electron. Syst. 26 6 Article 48 (June 2021) 20\u00a0pages. 10.1145\/3460971","DOI":"10.1145\/3460971"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49661.2025.10904543"},{"key":"e_1_3_3_1_72_2","unstructured":"Angelika Romanou Negar Foroutan Anna Sotnikova Zeming Chen Sree\u00a0Harsha Nelaturu Shivalika Singh Rishabh Maheshwary Micol Altomare Mohamed\u00a0A Haggag Alfonso Amayuelas et\u00a0al. 2024. INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.19799 (2024)."},{"key":"e_1_3_3_1_73_2","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter."},{"key":"e_1_3_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2014.94"},{"key":"e_1_3_3_1_75_2","unstructured":"Xiaoming Shi Shiyu Wang Yuqi Nie Dianqi Li Zhou Ye Qingsong Wen and Ming Jin. 2024. Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts. arxiv:https:\/\/arXiv.org\/abs\/2409.16040\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2409.16040"},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"crossref","unstructured":"Kevin Skadron Mircea\u00a0R Stan Wei Huang Sivakumar Velusamy Karthik Sankaranarayanan and David Tarjan. 2003. Temperature-aware microarchitecture. ACM SIGARCH Computer Architecture News 31 2 (2003) 2\u201313.","DOI":"10.1145\/871656.859620"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"crossref","unstructured":"Mircea\u00a0R Stan Kevin Skadron Marco Barcella Wei Huang Karthik Sankaranarayanan and Sivakumar Velusamy. 2003. Hotspot: A dynamic compact thermal model at the processor-architecture level. Microelectronics Journal 34 12 (2003) 1153\u20131165.","DOI":"10.1016\/S0026-2692(03)00206-4"},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"crossref","unstructured":"Aaron Stillmaker and Bevan Baas. 2017. Scaling equations for the accurate prediction of CMOS device performance from 180 nm to 7 nm. Integration 58 (2017) 74\u201381.","DOI":"10.1016\/j.vlsi.2017.02.002"},{"key":"e_1_3_3_1_79_2","unstructured":"Kimi Team Yifan Bai Yiping Bao Guanduo Chen Jiahao Chen Ningxin Chen Ruijue Chen Yanru Chen Yuankun Chen Yutian Chen Zhuofu Chen Jialei Cui Hao Ding Mengnan Dong Angang Du Chenzhuang Du Dikang Du Yulun Du Yu Fan Yichen Feng Kelin Fu Bofei Gao Hongcheng Gao Peizhong Gao Tong Gao Xinran Gu Longyu Guan Haiqing Guo Jianhang Guo Hao Hu Xiaoru Hao Tianhong He Weiran He Wenyang He Chao Hong Yangyang Hu Zhenxing Hu Weixiao Huang Zhiqi Huang Zihao Huang Tao Jiang Zhejun Jiang Xinyi Jin Yongsheng Kang Guokun Lai Cheng Li Fang Li Haoyang Li Ming Li Wentao Li Yanhao Li Yiwei Li Zhaowei Li Zheming Li Hongzhan Lin Xiaohan Lin Zongyu Lin Chengyin Liu Chenyu Liu Hongzhang Liu Jingyuan Liu Junqi Liu Liang Liu Shaowei Liu T.\u00a0Y. Liu Tianwei Liu Weizhou Liu Yangyang Liu Yibo Liu Yiping Liu Yue Liu Zhengying Liu Enzhe Lu Lijun Lu Shengling Ma Xinyu Ma Yingwei Ma Shaoguang Mao Jie Mei Xin Men Yibo Miao Siyuan Pan Yebo Peng Ruoyu Qin Bowen Qu Zeyu Shang Lidong Shi Shengyuan Shi Feifan Song Jianlin Su Zhengyuan Su Xinjie Sun Flood Sung Heyi Tang Jiawen Tao Qifeng Teng Chensi Wang Dinglu Wang Feng Wang Haiming Wang Jianzhou Wang Jiaxing Wang Jinhong Wang Shengjie Wang Shuyi Wang Yao Wang Yejie Wang Yiqin Wang Yuxin Wang Yuzhi Wang Zhaoji Wang Zhengtao Wang Zhexu Wang Chu Wei Qianqian Wei Wenhao Wu Xingzhe Wu Yuxin Wu Chenjun Xiao Xiaotong Xie Weimin Xiong Boyu Xu Jing Xu Jinjing Xu L.\u00a0H. Xu Lin Xu Suting Xu Weixin Xu Xinran Xu Yangchuan Xu Ziyao Xu Junjie Yan Yuzi Yan Xiaofei Yang Ying Yang Zhen Yang Zhilin Yang Zonghan Yang Haotian Yao Xingcheng Yao Wenjie Ye Zhuorui Ye Bohong Yin Longhui Yu Enming Yuan Hongbang Yuan Mengjie Yuan Haobing Zhan Dehao Zhang Hao Zhang Wanlu Zhang Xiaobin Zhang Yangkun Zhang Yizhi Zhang Yongting Zhang Yu Zhang Yutao Zhang Yutong Zhang Zheng Zhang Haotian Zhao Yikai Zhao Huabin Zheng Shaojie Zheng Jianren Zhou Xinyu Zhou Zaida Zhou Zhen Zhu Weiyu Zhuang and Xinxing Zu. 2025. Kimi K2: Open Agentic Intelligence. arxiv:https:\/\/arXiv.org\/abs\/2507.20534\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2507.20534"},{"key":"e_1_3_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2016.155"},{"key":"e_1_3_3_1_81_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention Is All You Need. CoRR abs\/1706.03762 (2017). arXiv:https:\/\/arXiv.org\/abs\/1706.03762http:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00096"},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4413"},{"key":"e_1_3_3_1_84_2","doi-asserted-by":"publisher","unstructured":"Xiangjin Wu Luke\u00a0R. Upton Jian Chen Po-Kai Hsu Shimeng Yu and H.-S.\u00a0Philip Wong. 2025. Signal Margin Density and Scalability of 3-D DRAM: A Comparative Study of Two Bitline Architectures. IEEE Transactions on Electron Devices 72 2 (2025) 671\u2013677. 10.1109\/TED.2024.3520074","DOI":"10.1109\/TED.2024.3520074"},{"key":"e_1_3_3_1_85_2","unstructured":"xAI. [n. d.]. Grok 3. https:\/\/grok.com\/. Accessed: 2025-03-02."},{"key":"e_1_3_3_1_86_2","unstructured":"Leyang Xue Yao Fu Zhan Lu Luo Mai and Mahesh Marina. 2025. MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache. arxiv:https:\/\/arXiv.org\/abs\/2401.14361\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.14361"},{"key":"e_1_3_3_1_87_2","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et\u00a0al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.15115 (2024)."},{"key":"e_1_3_3_1_88_2","unstructured":"Jinghan Yao Quentin Anthony Aamir Shafi Hari Subramoni Dhabaleswar K. and Panda. 2024. Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference. arxiv:https:\/\/arXiv.org\/abs\/2401.08383\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.08383"},{"key":"e_1_3_3_1_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00037"},{"key":"e_1_3_3_1_90_2","unstructured":"Sungmin Yun Kwanhee Kyung Juhwan Cho Jaewan Choi Jongmin Kim Byeongho Kim Sukhan Lee Kyomin Sohn and Jung\u00a0Ho Ahn. 2024. Duplex: A Device for Large Language Models with Mixture of Experts Grouped Query Attention and Continuous Batching. arxiv:https:\/\/arXiv.org\/abs\/2409.01141\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2409.01141"},{"key":"e_1_3_3_1_91_2","unstructured":"Susan Zhang Stephen Roller Naman Goyal Mikel Artetxe Moya Chen Shuohui Chen Christopher Dewan Mona Diab Xian Li Xi\u00a0Victoria Lin et\u00a0al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.01068 (2022)."},{"key":"e_1_3_3_1_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586212"},{"key":"e_1_3_3_1_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:49:48Z","timestamp":1769464188000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":92,"alternative-id":["10.1145\/3725843.3756043","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756043","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}