{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:53:33Z","timestamp":1771952013858,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"U.S. National Science Foundation","award":["CCF-2341039"],"award-info":[{"award-number":["CCF-2341039"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3721146.3721955","type":"proceedings-article","created":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T17:42:05Z","timestamp":1743529325000},"page":"46-55","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Understanding Oversubscribed Memory Management for Deep Learning Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1460-0766","authenticated-orcid":false,"given":"Mao","family":"Lin","sequence":"first","affiliation":[{"name":"University of California, Merced, Merced, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-8198","authenticated-orcid":false,"given":"Hyeran","family":"Jeon","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: a system for large-scale machine learning. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (Savannah, GA, USA) (OSDI'16). USENIX Association, USA, 265--283."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00023"},{"key":"e_1_3_2_1_3_1","unstructured":"PyTorch Open-Source Community. Accessed February 2025. PyTorch CUDA Caching Memory Allocator. https:\/\/github.com\/pytorch\/pytorch\/blob\/main\/c10\/cuda\/CUDACachingAllocator.cpp."},{"key":"e_1_3_2_1_4_1","unstructured":"NVIDIA Corporation. Accessed February 2025. Improving GPU Memory Oversubscription Performance. https:\/\/developer.nvidia.com\/blog\/improving-gpu-memory-oversubscription-performance\/."},{"key":"e_1_3_2_1_5_1","unstructured":"NVIDIA Corporation. Accessed February 2025. NVIDIA A100 80GB PCIe GPU. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/a100\/pdf\/PB-10577-001_v02.pdf."},{"key":"e_1_3_2_1_6_1","unstructured":"NVIDIA Corporation. Accessed February 2025. NVIDIA Grace Hopper Superchip Architecture Whitepaper. https:\/\/resources.nvidia.com\/en-us-grace-cpu\/nvidia-grace-hopper."},{"key":"e_1_3_2_1_7_1","unstructured":"NVIDIA Corporation. Accessed February 2025. NVIDIA Hopper Architecture In-Depth. https:\/\/developer.nvidia.com\/blog\/nvidia-hopper-architecture-in-depth\/."},{"key":"e_1_3_2_1_8_1","unstructured":"NVIDIA Corporation. Accessed February 2025. NVIDIA Nsight Systems: A system-wide performance analysis tool. https:\/\/developer.nvidia.com\/nsight-systems."},{"key":"e_1_3_2_1_9_1","unstructured":"NVIDIA Corporation. Accessed February 2025. NVIDIA Tesla P100 Whitepaper. https:\/\/images.nvidia.com\/content\/pdf\/tesla\/whitepaper\/pascal-architecture-whitepaper.pdf."},{"key":"e_1_3_2_1_10_1","unstructured":"NVIDIA Corporation. Accessed February 2025. Unified Memory in CUDA 6. https:\/\/developer.nvidia.com\/blog\/unified-memory-in-cuda-6\/."},{"key":"e_1_3_2_1_11_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_12_1","unstructured":"Xianzhong Ding Yunkai Zhang Binbin Chen Donghao Ying Tieying Zhang Jianjun Chen Lei Zhang Alberto Cerpa and Wan Du. 2023. Vmr2l: Virtual machines rescheduling using reinforcement learning in data centers."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717476"},{"key":"e_1_3_2_1_14_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9473982"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322224"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00054"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378530"},{"key":"e_1_3_2_1_20_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, and Xin Liu. 2024. MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 745--760. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/jiang-ziheng"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575736"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.37"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_24_1","volume-title":"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)","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). USENIX Association, Santa Clara, CA, 155--172. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/lee"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582044"},{"key":"e_1_3_2_1_28_1","unstructured":"The linux kernel development community. Accessed February 2025. Heterogeneous Memory Management (HMM). https:\/\/www.kernel.org\/doc\/html\/latest\/mm\/hmm.html."},{"key":"e_1_3_2_1_29_1","volume-title":"Proc. of ML Systems Workshop in NIPS","volume":"7","author":"Meng Chen","year":"2017","unstructured":"Chen Meng, Minmin Sun, Jun Yang, Minghui Qiu, and Yang Gu. 2017. Training deeper models by GPU memory optimization on TensorFlow. In Proc. of ML Systems Workshop in NIPS, Vol. 7."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_31_1","volume-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke Adam","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 Yang, Zach 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. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"17583","author":"Patil Shishir G.","year":"2022","unstructured":"Shishir G. Patil, Paras Jain, Prabal Dutta, Ion Stoica, and Joseph Gonzalez. 2022. POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 17573--17583. https:\/\/proceedings.mlr.press\/v162\/patil22b.html"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619590"},{"key":"e_1_3_2_1_35_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00066"},{"key":"e_1_3_2_1_37_1","unstructured":"Sam Stoelinga. Accessed February 2025. What GPUs can run Llama 3.1 405B? https:\/\/www.substratus.ai\/blog\/llama-3-1-405b-gpu-requirements."},{"key":"e_1_3_2_1_38_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507731"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"}],"event":{"name":"EuroMLSys '25: 5th Workshop on Machine Learning and Systems","location":"World Trade Center Rotterdam Netherlands","acronym":"EuroMLSys '25","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 5th Workshop on Machine Learning and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721146.3721955","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721146.3721955","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721146.3721955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:57:39Z","timestamp":1750298259000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721146.3721955"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":43,"alternative-id":["10.1145\/3721146.3721955","10.1145\/3721146"],"URL":"https:\/\/doi.org\/10.1145\/3721146.3721955","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-04-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}