{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:00:39Z","timestamp":1780664439829,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:00:00Z","timestamp":1777161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFB4502200"],"award-info":[{"award-number":["2023YFB4502200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62325405"],"award-info":[{"award-number":["62325405"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62504139"],"award-info":[{"award-number":["62504139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24B6015"],"award-info":[{"award-number":["U24B6015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["QY24247"],"award-info":[{"award-number":["QY24247"]}]},{"name":"Beijing Natural Science Foundation","award":["L242018"],"award-info":[{"award-number":["L242018"]}]},{"name":"Beijing Natural Science Foundation","award":["L257010"],"award-info":[{"award-number":["L257010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3769335","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"728-743","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["STAlloc: Enhancing Memory Efficiency in Large-Scale Model Training with Spatio-Temporal Planning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1273-2573","authenticated-orcid":false,"given":"Zixiao","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2085-4932","authenticated-orcid":false,"given":"Junhao","family":"Hu","sequence":"additional","affiliation":[{"name":"Infinigence-AI, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9990-5090","authenticated-orcid":false,"given":"Hao","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1921-4423","authenticated-orcid":false,"given":"Chunyang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Infinigence-AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8049-9233","authenticated-orcid":false,"given":"Yueran","family":"Tang","sequence":"additional","affiliation":[{"name":"Infinigence-AI, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0557-1104","authenticated-orcid":false,"given":"Quanlu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Infinigence-AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7108-7365","authenticated-orcid":false,"given":"Zhen","family":"Guo","sequence":"additional","affiliation":[{"name":"Infinigence-AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7286-122X","authenticated-orcid":false,"given":"Zhenhua","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3858-7972","authenticated-orcid":false,"given":"Shengen","family":"Yan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9259-7180","authenticated-orcid":false,"given":"Zhenhua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0849-3252","authenticated-orcid":false,"given":"Guohao","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6108-5157","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of GTC","volume":"152","author":"Adinetz Andrew V","year":"2014","unstructured":"Andrew V Adinetz and Dirk Pleiter. 2014. Halloc: a high-throughput dynamic memory allocator for GPGPU architectures. In Proceedings of GTC, Vol. 152."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858965.2814294"},{"key":"e_1_3_2_1_4_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of OSDI. 578\u2013594","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, et al. 2018. TVM: An automated End-to-End optimizing compiler for deep learning. In Proceedings of OSDI. 578\u2013594."},{"key":"e_1_3_2_1_6_1","volume-title":"Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174 (2016)."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of MLSys. 800\u2013811","author":"David Robert","year":"2021","unstructured":"Robert David, Jared Duke, Advait Jain, Vijay Janapa Reddi, Nat Jeffries, Jian Li, Nick Kreeger, Ian Nappier, Meghna Natraj, Tiezhen Wang, et al. 2021. Tensorflow lite micro: Embedded machine learning for tinyml systems. In Proceedings of MLSys. 800\u2013811."},{"key":"e_1_3_2_1_8_1","unstructured":"Jiangfei Duan Shuo Zhang Zerui Wang Lijuan Jiang Wenwen Qu Qinghao Hu Guoteng Wang Qizhen Weng Hang Yan Xingcheng Zhang et al. 2024. Efficient training of large language models on distributed infrastructures: a survey. arXiv preprint arXiv:2407.20018 (2024)."},{"key":"e_1_3_2_1_9_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_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295727"},{"key":"e_1_3_2_1_11_1","unstructured":"Ant Group. 2023. GMLake: GPU Memory Lake for Large Model Training. https:\/\/github.com\/antgroup\/glake."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640423"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/376656.376810"},{"key":"e_1_3_2_1_14_1","first-page":"497","article-title":"Checkmate: Breaking the memory wall with optimal tensor rematerialization","volume":"2","author":"Jain Paras","year":"2020","unstructured":"Paras Jain, Ajay Jain, Aniruddha Nrusimha, Amir Gholami, Pieter Abbeel, Joseph Gonzalez, Kurt Keutzer, and Ion Stoica. 2020. Checkmate: Breaking the memory wall with optimal tensor rematerialization. Proceedings of MLSys 2 (2020), 497\u2013511.","journal-title":"Proceedings of MLSys"},{"key":"e_1_3_2_1_15_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/301589.286864"},{"key":"e_1_3_2_1_17_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of MLSys. 341\u2013353","author":"Korthikanti Vijay Anand","year":"2023","unstructured":"Vijay Anand Korthikanti, Jared Casper, Sangkug Lym, Lawrence McAfee, Michael Andersch, Mohammad Shoeybi, and Bryan Catanzaro. 2023. Reducing activation recomputation in large transformer models. In Proceedings of MLSys. 341\u2013353."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3566097.3567913"},{"key":"e_1_3_2_1_20_1","volume-title":"Tflms: Large model support in tensorflow by graph rewriting. arXiv preprint arXiv:1807.02037","author":"Le Tung D","year":"2018","unstructured":"Tung D Le, Haruki Imai, Yasushi Negishi, and Kiyokuni Kawachiya. 2018. Tflms: Large model support in tensorflow by graph rewriting. arXiv preprint arXiv:1807.02037 (2018)."},{"key":"e_1_3_2_1_21_1","volume-title":"Gshard: Scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668","author":"Lepikhin Dmitry","year":"2020","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2020. Gshard: Scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668 (2020)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605613"},{"key":"e_1_3_2_1_23_1","unstructured":"Aixin Liu Bei Feng Bin Wang Bingxuan Wang Bo Liu Chenggang Zhao Chengqi Dengr Chong Ruan Damai Dai Daya Guo et al. 2024. Deepseek-v2: A strong economical and efficient mixture-of-experts language model. arXiv preprint arXiv:2405.04434 (2024)."},{"key":"e_1_3_2_1_24_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024. DeepSeek-V3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3567955.3567961"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375634.1375637"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings 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 Proceedings of ML Systems Workshop in NIPS, Vol. 7."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3623278.3624752"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of ICML. PMLR, 7937\u20137947","author":"Narayanan Deepak","year":"2021","unstructured":"Deepak Narayanan, Amar Phanishayee, Kaiyu Shi, Xie Chen, and Matei Zaharia. 2021. Memory-efficient pipeline-parallel dnn training. In Proceedings of ICML. PMLR, 7937\u20137947."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of SC. 1\u201315","author":"Narayanan Deepak","year":"2021","unstructured":"Deepak Narayanan, Mohammad Shoeybi, Jared Casper, Patrick LeGresley, Mostofa Patwary, Vijay Korthikanti, Dmitri Vainbrand, Prethvi Kashinkunti, Julie Bernauer, Bryan Catanzaro, et al. 2021. Efficient large-scale language model training on gpu clusters using megatronlm. In Proceedings of SC. 1\u201315."},{"key":"e_1_3_2_1_32_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","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, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_33_1","unstructured":"PyTorch. 2025. PyTorch Documentation. https:\/\/pytorch.org\/docs\/stable\/index.html."},{"key":"e_1_3_2_1_34_1","volume-title":"Zero bubble pipeline parallelism. arXiv preprint arXiv:2401.10241","author":"Qi Penghui","year":"2023","unstructured":"Penghui Qi, Xinyi Wan, Guangxing Huang, and Min Lin. 2023. Zero bubble pipeline parallelism. arXiv preprint arXiv:2401.10241 (2023)."},{"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\/SC41405.2020.00024"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of USENIX ATC 21","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. {Zero-offload}: Democratizing {billion-scale} model training. In Proceedings of USENIX ATC 21. 551\u2013564."},{"key":"e_1_3_2_1_39_1","volume-title":"Megatron-lm: Training multibillion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053","author":"Shoeybi Mohammad","year":"2019","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-lm: Training multibillion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053 (2019)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/360933.360949"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1133956.1133964"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339604"},{"key":"e_1_3_2_1_43_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Mihir Sanjay Kale, et al","author":"Team Gemma","year":"2024","unstructured":"Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivi\u00e8re, Mihir Sanjay Kale, et al. 2024. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295 (2024)."},{"key":"e_1_3_2_1_45_1","unstructured":"Qwen Team. 2024. Qwen1.5-MoE: Matching 7B Model Performance with 1\/3 Activated Parameters. https:\/\/qwenlm.github.io\/blog\/qwenmoe\/."},{"key":"e_1_3_2_1_46_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","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 al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2247684.2247693"},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of HPG. 19\u201327","author":"Vinkler Marek","year":"2014","unstructured":"Marek Vinkler, Vlastimil Havran, et al. 2014. Register efficient memory allocator for GPUs.. In Proceedings of HPG. 19\u201327."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2458523.2458535"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-60368-9_19"},{"key":"e_1_3_2_1_51_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_52_1","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)."}],"event":{"name":"EUROSYS '26: 21st European Conference on Computer Systems","location":"McEwan Hall\/The University of Edinburgh Edinburgh Scotland UK","acronym":"EUROSYS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3767295.3769335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:03:31Z","timestamp":1780661011000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3769335"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":52,"alternative-id":["10.1145\/3767295.3769335","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3769335","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}