{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T15:30:56Z","timestamp":1773588656665,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":79,"publisher":"ACM","funder":[{"name":"National Key Research &amp; Development Program of China","award":["2022YFB4500103"],"award-info":[{"award-number":["2022YFB4500103"]}]},{"name":"NSFC","award":["62402317"],"award-info":[{"award-number":["62402317"]}]},{"name":"NSFC","award":["62032008"],"award-info":[{"award-number":["62032008"]}]},{"name":"STCSM","award":["25LN3200900"],"award-info":[{"award-number":["25LN3200900"]}]},{"name":"STCSM","award":["24ZR1435500"],"award-info":[{"award-number":["24ZR1435500"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,22]]},"DOI":"10.1145\/3779212.3790212","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:55:26Z","timestamp":1773150926000},"page":"1622-1639","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["REPA:\n                    <u>Re<\/u>\n                    configurable\n                    <u>P<\/u>\n                    IM for the Joint\n                    <u>A<\/u>\n                    cceleration of KV Cache Offloading and Processing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2893-679X","authenticated-orcid":false,"given":"Yang","family":"Hong","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6103-2881","authenticated-orcid":false,"given":"Junlong","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6190-5327","authenticated-orcid":false,"given":"Bo","family":"Peng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1142-4496","authenticated-orcid":false,"given":"Jianguo","family":"Yao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2018.8351561"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLSID60093.2024.00100"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3232195.3232217"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3384012"},{"key":"e_1_3_2_1_5_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"e_1_3_2_1_6_1","volume-title":"EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents. In The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Chen Junting","year":"2025","unstructured":"Junting Chen, Checheng Yu, Xunzhe Zhou, Tianqi Xu, Yao Mu, Mengkang Hu, Wenqi Shao, Yikai Wang, Guohao Li, and Lin Shao. 2025. EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=Ey8KcabBpB"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2789723"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi Xiaokang Zhang Xingkai Yu Yu Wu Z. F. Wu Zhibin Gou Zhihong Shao Zhuoshu Li Ziyi Gao Aixin Liu Bing Xue Bingxuan Wang Bochao Wu Bei Feng Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai 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 Honghui Ding Huajian Xin Huazuo Gao Hui Qu Hui Li Jianzhong Guo Jiashi Li Jiawei Wang Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li J. L. Cai Jiaqi Ni Jian Liang Jin Chen Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Liang Zhao Litong Wang Liyue Zhang Lei Xu Leyi Xia Mingchuan Zhang Minghua Zhang Minghui Tang Meng Li Miaojun Wang Mingming Li Ning Tian Panpan Huang Peng Zhang Qiancheng Wang Qinyu Chen Qiushi Du Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang R. J. Chen R. L. Jin Ruyi Chen Shanghao Lu Shangyan Zhou Shanhuang Chen Shengfeng Ye Shiyu Wang Shuiping Yu Shunfeng Zhou Shuting Pan and S. S. Li. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. CoRR Vol. abs\/2501.12948 (2025). https:\/\/doi.org\/10.48550\/ARXIV.2501.12948 arXiv:2501.12948","DOI":"10.48550\/ARXIV.2501.12948"},{"key":"e_1_3_2_1_10_1","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. L. 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. J. Chen R. L. Jin Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang Runxin Xu Ruoyu Zhang Ruyi Chen S. S. 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. L. Xiao and Wangding Zeng. 2024. DeepSeek-V3 Technical Report. CoRR Vol. abs\/2412.19437 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2412.19437 arXiv:2412.19437"},{"key":"e_1_3_2_1_11_1","volume-title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Dong Harry","year":"2024","unstructured":"Harry Dong, Xinyu Yang, Zhenyu Zhang, Zhangyang Wang, Yuejie Chi, and Beidi Chen. 2024. Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=uhHDhVKFMW"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","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 Aur\u00e9lien Rodriguez Austen Gregerson Ava Spataru Baptiste Rozi\u00e8re 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 Canton 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 Michael Smith Filip Radenovic Frank Zhang Gabriel Synnaeve Gabrielle Lee Georgia Lewis Anderson Graeme Nail Gr\u00e9goire Mialon Guan Pang Guillem Cucurell Hailey Nguyen Hannah Korevaar Hu Xu Hugo Touvron Iliyan Zarov Imanol Arrieta Ibarra Isabel M. Kloumann Ishan Misra Ivan Evtimov Jade Copet Jaewon Lee Jan Geffert Jana Vranes Jason Park Jay Mahadeokar Jeet Shah Jelmer van der 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 Vasuden Alwala Kartikeya Upasani Kate Plawiak Ke Li Kenneth Heafield Kevin Stone and et al. 2024. The Llama 3 Herd of Models. CoRR Vol. abs\/2407.21783 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2407.21783 arXiv:2407.21783","DOI":"10.48550\/ARXIV.2407.21783"},{"key":"e_1_3_2_1_13_1","first-page":"111","volume-title":"Proceedings of the 2024 USENIX Annual Technical Conference, USENIX ATC 2024","author":"Gao Bin","year":"2024","unstructured":"Bin Gao, Zhuomin He, Puru Sharma, Qingxuan Kang, Djordje Jevdjic, Junbo Deng, Xingkun Yang, Zhou Yu, and Pengfei Zuo. 2024. Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention. In Proceedings of the 2024 USENIX Annual Technical Conference, USENIX ATC 2024, Santa Clara, CA, USA, July 10-12, 2024, Saurabh Bagchi and Yiying Zhang (Eds.). USENIX Association, 111-126. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/gao-bin-cost"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696072"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716267"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446749"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716009"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.17565"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.11181"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2025.3558009"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203782"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322237"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.997"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04196-6"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715996"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2013.6487708"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2014.7478812"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2021.3133945"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476184"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2014.2357292"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2015.2433536"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731073"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/nmat3070"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713923"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3012860"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3344524"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00065"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3594250"},{"key":"e_1_3_2_1_43_1","volume-title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024","author":"Liu Akide","year":"2024","unstructured":"Akide Liu, Jing Liu, Zizheng Pan, Yefei He, Reza Haffari, and Bohan Zhuang. 2024b. MiniCache: KV Cache Compression in Depth Dimension for Large Language Models. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub M. Tomczak, and Cheng Zhang (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/fd0705710bf01b88a60a3d479ea341d9-Abstract-Conference.html"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3290869"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V39I5.32588"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2013.6487703"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672274"},{"key":"e_1_3_2_1_48_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Liu Zichang","year":"2023","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. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/a452a7c6c463e4ae8fbdc614c6e983e6-Abstract-Conference.html"},{"key":"e_1_3_2_1_49_1","first-page":"203","volume-title":"Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies, FAST 2021","author":"Mohan Jayashree","year":"2021","unstructured":"Jayashree Mohan, Amar Phanishayee, and Vijay Chidambaram. 2021. CheckFreq: Frequent, Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies, FAST 2021, February 23-25, 2021, Marcos K. Aguilera and Gala Yadgar (Eds.). USENIX Association, 203-216. https:\/\/www.usenix.org\/conference\/fast21\/presentation\/mohan"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658617.3697572"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00113"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_11"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"e_1_3_2_1_54_1","volume-title":"High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Z. Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.). 8024-8035. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/bdbca288fee7f92f2bfa9f7012727740-Abstract.html"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM13553.2020.9372091"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the Sixth Conference on Machine Learning and Systems, MLSys 2023","author":"Pope Reiner","year":"2023","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. In Proceedings of the Sixth Conference on Machine Learning and Systems, MLSys 2023, Miami, FL, USA, June 4-8, 2023, Dawn Song, Michael Carbin, and Tianqi Chen (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/hash\/c4be71ab8d24cdfb45e3d06dbfca2780-Abstract-mlsys2023.html"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707256"},{"key":"e_1_3_2_1_59_1","volume-title":"Mooncake: Trading More Storage for Less Computation - A KVCache-centric Architecture for Serving LLM Chatbot. In 23rd USENIX Conference on File and Storage Technologies, FAST 2025","author":"Qin Ruoyu","year":"2025","unstructured":"Ruoyu Qin, Zheming Li, Weiran He, Jialei Cui, Feng Ren, Mingxing Zhang, Yongwei Wu, Weimin Zheng, and Xinran Xu. 2025. Mooncake: Trading More Storage for Less Computation - A KVCache-centric Architecture for Serving LLM Chatbot. In 23rd USENIX Conference on File and Storage Technologies, FAST 2025, Santa Clara, CA, February 25-27, 2025, Haryadi S. Gunawi and Vasily Tarasov (Eds.). USENIX Association, 155-170. https:\/\/www.usenix.org\/conference\/fast25\/presentation\/qin"},{"key":"e_1_3_2_1_60_1","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Rezazadeh Alireza","year":"2025","unstructured":"Alireza Rezazadeh, Zichao Li, Wei Wei, and Yujia Bao. 2025. From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=moXtEmCleY"},{"key":"e_1_3_2_1_61_1","volume-title":"International Conference on Machine Learning, ICML 2023","volume":"31116","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, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 31094-31116. https:\/\/proceedings.mlr.press\/v202\/sheng23a.html"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3656019.3676890"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature06932"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3496847"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton-Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aur\u00e9lien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. CoRR Vol. abs\/2307.09288 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2307.09288 arXiv:2307.09288","DOI":"10.48550\/ARXIV.2307.09288"},{"key":"e_1_3_2_1_66_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998-6008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2695880"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056056"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3659208"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.15115"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.FINDINGS-ACL.195"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415640"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2410.18517"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.ACL-LONG.623"},{"key":"e_1_3_2_1_76_1","volume-title":"Orca: A Distributed Serving System for Transformer-Based Generative Models. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A Distributed Serving System for Transformer-Based Generative Models. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022, Carlsbad, CA, USA, July 11-13, 2022, Marcos K. Aguilera and Hakim Weatherspoon (Eds.). USENIX Association, 521-538. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00029"},{"key":"e_1_3_2_1_78_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Zhang Zhenyu","year":"2023","unstructured":"Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher R\u00e9, Clark W. Barrett, Zhangyang Wang, and Beidi Chen. 2023. H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/6ceefa7b15572587b78ecfcebb2827f8-Abstract-Conference.html"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"}],"event":{"name":"ASPLOS '26: 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Pittsburgh PA USA","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T14:02:03Z","timestamp":1773583323000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779212.3790212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":79,"alternative-id":["10.1145\/3779212.3790212","10.1145\/3779212"],"URL":"https:\/\/doi.org\/10.1145\/3779212.3790212","relation":{},"subject":[],"published":{"date-parts":[[2026,3,22]]},"assertion":[{"value":"2026-03-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}