{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:33:13Z","timestamp":1763191993743,"version":"3.45.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229114","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["MOVie: GPU Memory Optimization for Large-Scale DNNs Training with Virtual Memory Management"],"prefix":"10.1109","author":[{"given":"Zijun","family":"Ma","sequence":"first","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiabao","family":"Tang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songlei","family":"Jian","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusong","family":"Tan","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref1"},{"article-title":"The llama 3 herd of models","year":"2024","author":"Dubey","key":"ref2"},{"article-title":"Gemini: a family of highly capable multimodal models","year":"2023","author":"Team","key":"ref3"},{"article-title":"Efficient training of large language models on distributed infrastructures: A survey","year":"2024","author":"Duan","key":"ref4"},{"article-title":"Finetune llms on your own consumer hardware using tools from pytorch and hugging face ecosystem","year":"2024","author":"Belkada","key":"ref5"},{"year":"2025","key":"ref6","article-title":"Geforce rtx 5090"},{"key":"ref7","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"265","article-title":"{TensorFlow}: a system for {Large-Scale} machine learning","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi"},{"year":"2024","key":"ref9","article-title":"Pytorch memory management"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640423"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"article-title":"Training deep nets with sublinear memory cost","year":"2016","author":"Chen","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3281931"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"article-title":"Profile-guided memory optimization for deep neural networks","year":"2018","author":"Sekiyama","key":"ref15"},{"article-title":"Roam: memory-efficient large dnn training via optimized operator ordering and memory layout","year":"2023","author":"Shu","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532394"},{"key":"ref18","first-page":"32618","article-title":"Model: memory optimizations for deep learning","volume-title":"International Conference on Machine Learning","author":"Steiner"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3652024.3665508"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00030"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392684"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538928"},{"key":"ref23","article-title":"Coop: Memory is not a commodity","volume":"36","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Introducing low-level gpu virtual memory management","year":"2020","author":"Perry","key":"ref24"},{"year":"2023","key":"ref25","article-title":"zdevito: Expandable blocks in allocator"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"article-title":"Opt: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"year":"2023","key":"ref29","article-title":"Deepspeed-chat models and datasets"},{"article-title":"Mobilellm: Optimizing sub-billion parameter language models for on-device use cases","year":"2024","author":"Liu","key":"ref30"},{"article-title":"A conversational paradigm for program synthesis","year":"2022","author":"Nijkamp","key":"ref31"},{"article-title":"Code-gen2: Lessons for training llms on programming and natural languages","year":"2023","author":"Nijkamp","key":"ref32"},{"article-title":"Tinyllama: An open-source small language model","year":"2024","author":"Zhang","key":"ref33"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229114.pdf?arnumber=11229114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:29:39Z","timestamp":1763191779000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229114\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229114","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}