{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T15:46:57Z","timestamp":1791388017315,"version":"4.3.3"},"publisher-location":"New York, NY, USA","reference-count":100,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T00:00:00Z","timestamp":1792195200000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DARPA","award":["ACE, one of the seven centers in JUMP 2.0, a Semiconductor Research Corporation (SRC) program"],"award-info":[{"award-number":["ACE, one of the seven centers in JUMP 2.0, a Semiconductor Research Corporation (SRC) program"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756071","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"18-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Kelle: Co-design KV Caching and eDRAM for Efficient LLM Serving in Edge Computing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4376-0885","authenticated-orcid":false,"given":"Tianhua","family":"Xia","sequence":"first","affiliation":[{"name":"Tandon School of Engineering, New York University, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4815-9235","authenticated-orcid":false,"given":"Sai Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tandon School of Engineering, New York University, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"[n. d.]. Nangate freepdk45 open cell library. https:\/\/silvaco.com\/services\/library-design\/"},{"key":"e_1_3_3_1_3_2","unstructured":"[n. d.]. NVIDIA Jetson Orin. https:\/\/www.siliconhighwaydirect.com\/product-p\/900-13767-0000-000.htm."},{"key":"e_1_3_3_1_4_2","unstructured":"[n. d.]. pynvml: Python Bindings for the NVIDIA Management Library. https:\/\/pypi.org\/project\/pynvml\/."},{"key":"e_1_3_3_1_5_2","unstructured":"Griffin Adams Faisal Ladhak Hailey Schoelkopf and Raja Biswas. 2024. Cold Compress: A Toolkit for Benchmarking KV Cache Compression Approaches. https:\/\/www.answer.ai\/posts\/2024-08-01-cold-compress.html"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835978"},{"key":"e_1_3_3_1_7_2","unstructured":"Saleh Ashkboos Amirkeivan Mohtashami Maximilian\u00a0L Croci Bo Li Martin Jaggi Dan Alistarh Torsten Hoefler and James Hensman. 2024. Quarot: Outlier-free 4-bit inference in rotated llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.00456 (2024)."},{"key":"e_1_3_3_1_8_2","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et\u00a0al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.13923 (2025)."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Rajeev Balasubramonian Andrew\u00a0B. Kahng Naveen Muralimanohar Ali Shafiee and Vaishnav Srinivas. 2017. CACTI 7: New Tools for Interconnect Exploration in Innovative Off-Chip Memories. ACM Trans. Archit. Code Optim. 14 2 Article 14 (June 2017) 25\u00a0pages. 10.1145\/3085572","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"B.\u00a0Jayant Baliga. 2019. Synopsys. Wide Bandgap Semiconductor Power Devices (2019). https:\/\/api.semanticscholar.org\/CorpusID:239327327","DOI":"10.1016\/B978-0-08-102306-8.00011-3"},{"key":"e_1_3_3_1_11_2","volume-title":"AAAI Conference on Artificial Intelligence","author":"Bisk Yonatan","year":"2019","unstructured":"Yonatan Bisk, Rowan Zellers, Ronan\u00a0Le Bras, Jianfeng Gao, and Yejin Choi. 2019. PIQA: Reasoning about Physical Commonsense in Natural Language. In AAAI Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:208290939"},{"key":"e_1_3_3_1_12_2","unstructured":"Tom\u00a0B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.14165 (2020)."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00099"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522314"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Jiasi Chen and Xukan Ran. 2019. Deep learning with edge computing: A review. Proc. IEEE 107 8 (2019) 1655\u20131674.","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2627369.2627626"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Ki\u00a0Chul Chun Pulkit Jain Jung\u00a0Hwa Lee and Chris\u00a0H. Kim. 2011. A 3T Gain Cell Embedded DRAM Utilizing Preferential Boosting for High Density and Low Power On-Die Caches. IEEE Journal of Solid-State Circuits 46 6 (2011) 1495\u20131505. 10.1109\/JSSC.2011.2128150","DOI":"10.1109\/JSSC.2011.2128150"},{"key":"e_1_3_3_1_19_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 abs\/1803.05457 (2018). https:\/\/api.semanticscholar.org\/CorpusID:3922816"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Pradeep Dasigi Kyle Lo Iz Beltagy Arman Cohan Noah\u00a0A Smith and Matt Gardner. 2021. A dataset of information-seeking questions and answers anchored in research papers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2105.03011 (2021).","DOI":"10.18653\/v1\/2021.naacl-main.365"},{"key":"e_1_3_3_1_21_2","unstructured":"Jyotikrishna Dass Shang Wu Huihong Shi Chaojian Li Zhifan Ye Zhongfeng Wang and Yingyan Lin. 2022. ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention. arxiv:https:\/\/arXiv.org\/abs\/2211.05109\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2211.05109"},{"key":"e_1_3_3_1_22_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten 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 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 Frank Zhang Gabriel Synnaeve Gabrielle Lee Georgia\u00a0Lewis Anderson 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 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 Kartikeya Upasani Kate Plawiak Ke Li Kenneth Heafield Kevin Stone Khalid El-Arini Krithika Iyer Kshitiz Malik Kuenley Chiu Kunal Bhalla 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 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 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 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 Vladan Petrovic Weiwei Chu Wenhan Xiong Wenyin Fu Whitney Meers Xavier Martinet Xiaodong Wang Xiaoqing\u00a0Ellen Tan 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 Aaron Grattafiori Abha Jain Adam Kelsey Adam Shajnfeld Adithya Gangidi Adolfo Victoria Ahuva Goldstand Ajay Menon Ajay Sharma Alex Boesenberg Alex Vaughan Alexei Baevski Allie Feinstein Amanda Kallet Amit Sangani Anam Yunus Andrei Lupu Andres Alvarado Andrew Caples Andrew Gu Andrew Ho Andrew Poulton Andrew Ryan Ankit Ramchandani Annie Franco 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 Changhan Wang Changkyu Kim Chao Zhou Chester Hu Ching-Hsiang Chu Chris Cai Chris Tindal Christoph Feichtenhofer Damon Civin Dana Beaty Daniel Kreymer Daniel Li Danny Wyatt 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 Erik Brinkman Esteban Arcaute Evan Dunbar Evan Smothers Fei Sun Felix Kreuk Feng Tian Firat Ozgenel Francesco Caggioni Francisco Guzm\u00e1n Frank Kanayet Frank Seide Gabriela\u00a0Medina Florez Gabriella Schwarz Gada Badeer Georgia Swee Gil Halpern Govind Thattai Grant Herman Grigory Sizov Guangyi Zhang Guna Lakshminarayanan Hamid Shojanazeri Han Zou Hannah Wang Hanwen Zha Haroun Habeeb Harrison Rudolph Helen Suk Henry Aspegren Hunter Goldman Ibrahim Damlaj Igor Molybog Igor Tufanov Irina-Elena Veliche Itai Gat Jake Weissman James Geboski James Kohli 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 Karthik Prasad Kartikay Khandelwal Katayoun Zand Kathy Matosich Kaushik Veeraraghavan Kelly Michelena Keqian Li Kun Huang Kunal Chawla Kushal Lakhotia 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 Maria Tsimpoukelli Martynas Mankus Matan Hasson Matthew Lennie Matthias Reso Maxim Groshev Maxim Naumov Maya Lathi Meghan Keneally 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 Nikolay\u00a0Pavlovich Laptev Ning Dong Ning Zhang 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 Raymond Li Rebekkah Hogan Robin Battey Rocky Wang Rohan Maheswari Russ Howes Ruty Rinott Sai\u00a0Jayesh Bondu Samyak Datta Sara Chugh Sara Hunt Sargun Dhillon Sasha Sidorov Satadru Pan Saurabh Verma Seiji Yamamoto Sharadh Ramaswamy Shaun Lindsay Shaun Lindsay Sheng Feng Shenghao Lin Shengxin\u00a0Cindy Zha 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 Sungmin Cho Sunny Virk Suraj Subramanian Sy Choudhury Sydney Goldman Tal Remez Tamar Glaser Tamara Best Thilo Kohler 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 V\u00edtor Albiero Vlad Ionescu Vlad Poenaru Vlad\u00a0Tiberiu Mihailescu Vladimir Ivanov Wei Li Wenchen Wang Wenwen Jiang Wes Bouaziz Will Constable Xiaocheng Tang Xiaofang Wang Xiaojian Wu Xiaolan Wang Xide Xia Xilun Wu Xinbo Gao Yanjun Chen Ye Hu Ye Jia Ye Qi Yenda Li Yilin Zhang Ying Zhang Yossi Adi Youngjin Nam Yu Wang Yuchen Hao Yundi Qian Yuzi He Zach Rait Zachary DeVito Zef Rosnbrick Zhaoduo Wen Zhenyu Yang and Zhiwei Zhao. 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_23_2","volume-title":"Intel eDRAM Attacks Graphics in Pre 3-D IC Days","author":"Times EE","year":"2013","unstructured":"EE Times. 2013. Intel eDRAM Attacks Graphics in Pre 3-D IC Days. http:\/\/www.eetimes.com\/document.asp?doc_id=1263303"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS48785.2022.9937659"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Eric\u00a0J Fluhr Steve Baumgartner David Boerstler John\u00a0F Bulzacchelli Timothy Diemoz Daniel Dreps George English Joshua Friedrich Anne Gattiker Tilman Gloekler et\u00a0al. 2014. The 12-core power8\u2122 processor with 7.6 tb\/s io bandwidth integrated voltage regulation and resonant clocking. IEEE Journal of Solid-State Circuits 50 1 (2014) 10\u201323.","DOI":"10.1109\/JSSC.2014.2358553"},{"key":"e_1_3_3_1_26_2","unstructured":"Elias Frantar Saleh Ashkboos Torsten Hoefler and Dan Alistarh. 2022. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.17323 (2022)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5371628"},{"key":"e_1_3_3_1_28_2","unstructured":"Suyu Ge Yunan Zhang Liyuan Liu Minjia Zhang Jiawei Han and Jianfeng Gao. 2023. Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs. ArXiv abs\/2310.01801 (2023). https:\/\/api.semanticscholar.org\/CorpusID:263609075"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Robert Giterman Amir Shalom Andreas Burg Alexander Fish and Adam Teman. 2020. A 1-Mbit Fully Logic-Compatible 3T Gain-Cell Embedded DRAM in 16-nm FinFET. IEEE Solid-State Circuits Letters 3 (2020) 110\u2013113. 10.1109\/LSSC.2020.3006496","DOI":"10.1109\/LSSC.2020.3006496"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Robert Giterman Amir Shalom Andreas Burg Alexander Fish and Adam Teman. 2020. A 1-Mbit Fully Logic-Compatible 3T Gain-Cell Embedded DRAM in 16-nm FinFET. IEEE Solid-State Circuits Letters 3 (2020) 110\u2013113. 10.1109\/LSSC.2020.3006496","DOI":"10.1109\/LSSC.2020.3006496"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Cong Guo Jiaming Tang Weiming Hu Jingwen Leng Chen Zhang Fan Yang Yun-Bo Liu Minyi Guo and Yuhao Zhu. 2023. OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization. Proceedings of the 50th Annual International Symposium on Computer Architecture (2023). https:\/\/api.semanticscholar.org\/CorpusID:258179335","DOI":"10.1145\/3579371.3589038"},{"key":"e_1_3_3_1_32_2","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1606.08415 (2016)."},{"key":"e_1_3_3_1_33_2","unstructured":"Coleman Hooper Sehoon Kim Hiva Mohammadzadeh Michael\u00a0W. Mahoney Yakun\u00a0Sophia Shao Kurt Keutzer and Amir Gholami. 2024. KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization. arxiv:https:\/\/arXiv.org\/abs\/2401.18079\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.18079"},{"key":"e_1_3_3_1_34_2","unstructured":"Yunhai Hu Zining Liu Zhenyuan Dong Tianfan Peng Bradley McDanel and Sai\u00a0Qian Zhang. 2025. Speculative decoding and beyond: An in-depth survey of techniques. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.19732 (2025)."},{"key":"e_1_3_3_1_35_2","unstructured":"Yunhai Hu Tianhua Xia Zining Liu Rahul Raman Xingyu Liu Bo Bao Eric Sather Vithursan Thangarasa and Sai\u00a0Qian Zhang. 2025. DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.19201 (2025)."},{"key":"e_1_3_3_1_36_2","unstructured":"Albert\u00a0Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L\u00e9lio\u00a0Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven\u00a0Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William\u00a0El Sayed. 2023. Mistral 7B. arxiv:https:\/\/arXiv.org\/abs\/2310.06825\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"e_1_3_3_1_37_2","unstructured":"Mandar Joshi Eunsol Choi Daniel\u00a0S Weld and Luke Zettlemoyer. 2017. Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1705.03551 (2017)."},{"key":"e_1_3_3_1_38_2","volume-title":"Embedded Flash and DRAM Components","author":"Technology Kingston","year":"2024","unstructured":"Kingston Technology. 2024. Embedded Flash and DRAM Components. https:\/\/www.kingston.com\/en\/solutions\/embedded-and-industrial"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEST.2008.4700556"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"HT Kung. 1986. Memory requirements for balanced computer architectures. ACM SIGARCH Computer Architecture News 14 2 (1986) 49\u201354.","DOI":"10.1145\/17356.17362"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Jungi Lee Wonbeom Lee and Jaewoong Sim. 2024. Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization. 2024 ACM\/IEEE 51st Annual International Symposium on Computer Architecture (ISCA) (2024) 1048\u20131062. https:\/\/api.semanticscholar.org\/CorpusID:270620037","DOI":"10.1109\/ISCA59077.2024.00080"},{"key":"e_1_3_3_1_42_2","first-page":"155","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Lee Wonbeom","year":"2024","unstructured":"Wonbeom Lee, Jungi Lee, Junghwan Seo, and Jaewoong Sim. 2024. { InfiniGen} : Efficient generative inference of large language models with dynamic { KV} cache management. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 155\u2013172."},{"key":"e_1_3_3_1_43_2","first-page":"19274","volume-title":"International Conference on Machine Learning","author":"Leviathan Yaniv","year":"2023","unstructured":"Yaniv Leviathan, Matan Kalman, and Yossi Matias. 2023. Fast inference from transformers via speculative decoding. In International Conference on Machine Learning. PMLR, 19274\u201319286."},{"key":"e_1_3_3_1_44_2","unstructured":"Stephanie Lin Jacob Hilton and Owain Evans. 2022. TruthfulQA: Measuring How Models Mimic Human Falsehoods. arxiv:https:\/\/arXiv.org\/abs\/2109.07958\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2109.07958"},{"key":"e_1_3_3_1_45_2","unstructured":"Akide Liu Jing Liu Zizheng Pan Yefei He Gholamreza Haffari and Bohan Zhuang. 2024. MiniCache: KV Cache Compression in Depth Dimension for Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.14366 (2024)."},{"key":"e_1_3_3_1_46_2","unstructured":"Hanxiao Liu Zihang Dai David So and Quoc\u00a0V Le. 2021. Pay attention to mlps. Advances in neural information processing systems 34 (2021) 9204\u20139215."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Lian Liu Haimeng Ren Long Cheng Zhaohui Xu Yudong Pan Mengdi Wang Xiaowei Li Yinhe Han and Ying Wang. 2024. COMET: Towards Partical W4A4KV4 LLMs Serving. arxiv:https:\/\/arXiv.org\/abs\/2410.12168\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2410.12168","DOI":"10.1145\/3676641.3716252"},{"key":"e_1_3_3_1_48_2","unstructured":"Zichang Liu Aditya Desai Fangshuo Liao Weitao Wang Victor Xie Zhaozhuo Xu Anastasios Kyrillidis and Anshumali Shrivastava. 2023. Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time. ArXiv abs\/2305.17118 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258947558"},{"key":"e_1_3_3_1_49_2","unstructured":"Zirui Liu Jiayi Yuan Hongye Jin Shaochen Zhong Zhaozhuo Xu Vladimir Braverman Beidi Chen and Xia Hu. 2024. KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache. ArXiv abs\/2402.02750 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267413049"},{"key":"e_1_3_3_1_50_2","series-title":"(ICML\u201924)","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Liu Zirui","year":"2024","unstructured":"Zirui Liu, Jiayi Yuan, Hongye Jin, Shaochen\u00a0(Henry) Zhong, Zhaozhuo Xu, Vladimir Braverman, Beidi Chen, and Xia Hu. 2024. KIVI: a tuning-free asymmetric 2bit quantization for KV cache. In Proceedings of the 41st International Conference on Machine Learning (Vienna, Austria) (ICML\u201924). JMLR.org, Article 1311, 13\u00a0pages."},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"crossref","unstructured":"Bradley McDanel Sai\u00a0Qian Zhang Yunhai Hu and Zining Liu. 2025. PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decoding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.01572 (2025).","DOI":"10.18653\/v1\/2025.findings-acl.669"},{"key":"e_1_3_3_1_53_2","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer Sentinel Mixture Models. arxiv:https:\/\/arXiv.org\/abs\/1609.07843\u00a0[cs.CL]"},{"key":"e_1_3_3_1_54_2","unstructured":"Ramesh Nallapati Bowen Zhou Cicero\u00a0Nogueira dos santos Caglar Gulcehre and Bing Xiang. 2016. Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond. arxiv:https:\/\/arXiv.org\/abs\/1602.06023\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1602.06023"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317915"},{"key":"e_1_3_3_1_56_2","unstructured":"NVIDIA Corporation. 2024. NVIDIA System Management Interface (nvidia-smi). https:\/\/developer.nvidia.com\/system-management-interface."},{"key":"e_1_3_3_1_57_2","unstructured":"Xiurui Pan Endian Li Qiao Li Shengwen Liang Yizhou Shan Ke Zhou Yingwei Luo Xiaolin Wang and Jie Zhang. 2024. Instinfer: In-storage attention offloading for cost-effective long-context llm inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.04992 (2024)."},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00063"},{"key":"e_1_3_3_1_59_2","unstructured":"Alicia Parrish Angelica Chen Nikita Nangia Vishakh Padmakumar Jason Phang Jana Thompson Phu\u00a0Mon Htut and Samuel\u00a0R. Bowman. 2022. BBQ: A Hand-Built Bias Benchmark for Question Answering. arxiv:https:\/\/arXiv.org\/abs\/2110.08193\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2110.08193"},{"key":"e_1_3_3_1_60_2","unstructured":"Reiner Pope Sholto Douglas Aakanksha Chowdhery Jacob Devlin James Bradbury Jonathan Heek Kefan Xiao Shivani Agrawal and Jeff Dean. 2023. Efficiently scaling transformer inference. Proceedings of Machine Learning and Systems 5 (2023) 606\u2013624."},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.7873\/DATE.2015.0733"},{"key":"e_1_3_3_1_62_2","unstructured":"Team PyTorch. 2023. Accelerating generative ai with pytorch ii: Gpt fast.https:\/\/pytorch.org\/blog\/accelerating-generative-ai-2\/"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716013"},{"key":"e_1_3_3_1_64_2","unstructured":"Alec Radford. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_3_1_65_2","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. https:\/\/api.semanticscholar.org\/CorpusID:160025533"},{"key":"e_1_3_3_1_66_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_1_67_2","unstructured":"Jack\u00a0W Rae Anna Potapenko Siddhant\u00a0M Jayakumar and Timothy\u00a0P Lillicrap. 2019. Compressive transformers for long-range sequence modelling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1911.05507 (2019)."},{"key":"e_1_3_3_1_68_2","unstructured":"Haihao Shen Hanwen Chang Bo Dong Yu Luo and Hengyu Meng. 2023. Efficient LLM Inference on CPUs. arxiv:https:\/\/arXiv.org\/abs\/2311.00502\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2311.00502"},{"key":"e_1_3_3_1_69_2","first-page":"31094","volume-title":"International Conference on Machine Learning","author":"Sheng Ying","year":"2023","unstructured":"Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Beidi Chen, Percy Liang, Christopher R\u00e9, Ion Stoica, and Ce Zhang. 2023. Flexgen: High-throughput generative inference of large language models with a single gpu. In International Conference on Machine Learning. PMLR, 31094\u201331116."},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"crossref","unstructured":"Weisong Shi Jie Cao Quan Zhang Youhuizi Li and Lanyu Xu. 2016. Edge computing: Vision and challenges. IEEE internet of things journal 3 5 (2016) 637\u2013646.","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"e_1_3_3_1_71_2","volume-title":"Accelerating Generative AI at the Edge","author":"Soriaga J.","year":"2023","unstructured":"J. Soriaga. 2023. Accelerating Generative AI at the Edge. https:\/\/www.qualcomm.com\/news\/onq\/2023\/11\/accelerating-generative-ai-at-the-edge [Online; accessed 29-Mar-2025]."},{"key":"e_1_3_3_1_72_2","unstructured":"Jacob\u00a0R. Stevens Rangharajan Venkatesan Steve Dai Brucek Khailany and Anand Raghunathan. 2021. Softermax: Hardware\/Software Co-Design of an Efficient Softmax for Transformers. arxiv:https:\/\/arXiv.org\/abs\/2103.09301\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2103.09301"},{"key":"e_1_3_3_1_73_2","unstructured":"Manu Suryavansh. 2020. Google Coral Edge TPU Board Vs NVIDIA Jetson Nano Dev board Hardware Comparison."},{"key":"e_1_3_3_1_74_2","unstructured":"Qwen Team. 2024. Qwen2 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.10671 (2024)."},{"key":"e_1_3_3_1_75_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13971 (2023)."},{"key":"e_1_3_3_1_76_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00037"},{"key":"e_1_3_3_1_78_2","unstructured":"Hongyu Wang Shuming Ma Li Dong Shaohan Huang Huaijie Wang Lingxiao Ma Fan Yang Ruiping Wang Yi Wu and Furu Wei. 2023. BitNet: Scaling 1-bit Transformers for Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2310.11453\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.11453"},{"key":"e_1_3_3_1_79_2","doi-asserted-by":"crossref","unstructured":"Hanrui Wang Zhekai Zhang and Song Han. 2020. SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning. 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA) (2020) 97\u2013110. https:\/\/api.semanticscholar.org\/CorpusID:229298088","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_3_1_80_2","doi-asserted-by":"crossref","unstructured":"Xiaotian Wang Teng Tian Letian Zhao Wei Wu and Xi Jin. 2022. Exploration of balanced design in resource-constrained edge device for efficient CNNs. IEEE Transactions on Circuits and Systems II: Express Briefs 69 11 (2022) 4573\u20134577.","DOI":"10.1109\/TCSII.2022.3183258"},{"key":"e_1_3_3_1_81_2","doi-asserted-by":"crossref","unstructured":"Dieter\u00a0F Wendel Ron Kalla James Warnock Robert Cargnoni Sam\u00a0G Chu Joachim\u00a0G Clabes Daniel Dreps David Hrusecky Josh Friedrich Saiful Islam et\u00a0al. 2010. POWER7\u2122 a highly parallel scalable multi-core high end server processor. IEEE Journal of Solid-State Circuits 46 1 (2010) 145\u2013161.","DOI":"10.1109\/JSSC.2010.2080611"},{"key":"e_1_3_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3665314.3670816"},{"key":"e_1_3_3_1_83_2","unstructured":"Jingyang Xiang and Sai\u00a0Qian Zhang. 2024. DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.00648 (2024)."},{"key":"e_1_3_3_1_84_2","unstructured":"Guangxuan Xiao Yuandong Tian Beidi Chen Song Han and Mike Lewis. 2024. Efficient Streaming Language Models with Attention Sinks. arxiv:https:\/\/arXiv.org\/abs\/2309.17453\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2309.17453"},{"key":"e_1_3_3_1_85_2","doi-asserted-by":"crossref","unstructured":"Kai Xiao Jing Wan Hui Xie Yuxuan Zhu Tian Tian Wei Zhang Yingxin Chen Jinshu Zhang Lihui Zhou Sheng Dai et\u00a0al. 2024. High performance Si-MoS2 heterogeneous embedded DRAM. Nature Communications 15 1 (2024) 9782.","DOI":"10.1038\/s41467-024-54218-w"},{"key":"e_1_3_3_1_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715991"},{"key":"e_1_3_3_1_87_2","unstructured":"Daliang Xu Hao Zhang Liming Yang Ruiqi Liu Gang Huang Mengwei Xu and Xuanzhe Liu. 2024. Fast On-device LLM Inference with NPUs. arxiv:https:\/\/arXiv.org\/abs\/2407.05858\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2407.05858"},{"key":"e_1_3_3_1_88_2","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang Guanting Dong Haoran Wei Huan Lin Jialong Tang Jialin Wang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Ma Jianxin Yang Jin Xu Jingren Zhou Jinze Bai Jinzheng He Junyang Lin Kai Dang Keming Lu Keqin Chen Kexin Yang Mei Li Mingfeng Xue Na Ni Pei Zhang Peng Wang Ru Peng Rui Men Ruize Gao Runji Lin Shijie Wang Shuai Bai Sinan Tan Tianhang Zhu Tianhao Li Tianyu Liu Wenbin Ge Xiaodong Deng Xiaohuan Zhou Xingzhang Ren Xinyu Zhang Xipin Wei Xuancheng Ren Xuejing Liu Yang Fan Yang Yao Yichang Zhang Yu Wan Yunfei Chu Yuqiong Liu Zeyu Cui Zhenru Zhang Zhifang Guo and Zhihao Fan. 2024. Qwen2 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2407.10671\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_3_1_89_2","doi-asserted-by":"crossref","unstructured":"Dongjie Yang XiaoDong Han Yan Gao Yao Hu Shilin Zhang and Hai Zhao. 2024. PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.12532 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.195"},{"key":"e_1_3_3_1_90_2","doi-asserted-by":"crossref","unstructured":"Chengshuo Yu Taegeun Yoo Hyunjoon Kim Tony Tae-Hyoung Kim Kevin Chai\u00a0Tshun Chuan and Bongjin Kim. 2020. A logic-compatible eDRAM compute-in-memory with embedded ADCs for processing neural networks. IEEE Transactions on Circuits and Systems I: Regular Papers 68 2 (2020) 667\u2013679.","DOI":"10.1109\/TCSI.2020.3036209"},{"key":"e_1_3_3_1_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00108"},{"key":"e_1_3_3_1_92_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658473"},{"key":"e_1_3_3_1_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"e_1_3_3_1_94_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00082"},{"key":"e_1_3_3_1_95_2","doi-asserted-by":"publisher","unstructured":"Mingjin Zhang Xiaoming Shen Jiannong Cao Zeyang Cui and Shan Jiang. 2024. EdgeShard: Efficient LLM Inference via Collaborative Edge Computing. IEEE Internet of Things Journal (2024) 1\u20131. 10.1109\/JIOT.2024.3524255","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"e_1_3_3_1_96_2","unstructured":"Susan Zhang Stephen Roller Naman Goyal Mikel Artetxe Moya Chen Shuohui Chen Christopher Dewan Mona Diab Xian Li Xi\u00a0Victoria Lin Todor Mihaylov Myle Ott Sam Shleifer Kurt Shuster Daniel Simig Punit\u00a0Singh Koura Anjali Sridhar Tianlu Wang and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. arxiv:https:\/\/arXiv.org\/abs\/2205.01068\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2205.01068"},{"key":"e_1_3_3_1_97_2","doi-asserted-by":"crossref","unstructured":"Sai\u00a0Qian Zhang Bradley McDanel and H.\u00a0T. Kung. 2021. FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding. 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA) (2021) 846\u2013860. https:\/\/api.semanticscholar.org\/CorpusID:240288620","DOI":"10.1109\/HPCA53966.2022.00067"},{"key":"e_1_3_3_1_98_2","unstructured":"Sai\u00a0Qian Zhang Thierry Tambe Nestor Cuevas Gu-Yeon Wei and David Brooks. 2023. CAMEL: Co-Designing AI Models and Embedded DRAMs for Efficient On-Device Learning. arxiv:https:\/\/arXiv.org\/abs\/2305.03148\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2305.03148"},{"key":"e_1_3_3_1_99_2","unstructured":"Zhenyu\u00a0(Allen) Zhang Ying Sheng Tianyi Zhou Tianlong Chen Lianmin Zheng Ruisi Cai Zhao Song Yuandong Tian Christopher R\u00e9 Clark\u00a0W. Barrett Zhangyang Wang and Beidi Chen. 2023. H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models. ArXiv abs\/2306.14048 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259263947"},{"key":"e_1_3_3_1_100_2","doi-asserted-by":"crossref","unstructured":"Youpeng Zhao Di Wu and Jun Wang. 2024. ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.17312 (2024).","DOI":"10.1109\/ISCA59077.2024.00077"},{"key":"e_1_3_3_1_101_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\/3725843.3756071","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:42:26Z","timestamp":1769463746000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":100,"alternative-id":["10.1145\/3725843.3756071","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756071","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"}}]}}