{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:05:06Z","timestamp":1780664706242,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":58,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3769369","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"1879-1893","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Zeppelin: Balancing Variable-length Workloads in Data Parallel Large Model Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6416-7172","authenticated-orcid":false,"given":"Chang","family":"Chen","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8071-2552","authenticated-orcid":false,"given":"Tiancheng","family":"Chen","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6327-2033","authenticated-orcid":false,"given":"Jiangfei","family":"Duan","sequence":"additional","affiliation":[{"name":"CUHK, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5021-2912","authenticated-orcid":false,"given":"Qianchao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8081-8469","authenticated-orcid":false,"given":"Zerui","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1034-7502","authenticated-orcid":false,"given":"Qinghao","family":"Hu","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8456-0491","authenticated-orcid":false,"given":"Peng","family":"Sun","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4896-121X","authenticated-orcid":false,"given":"Xiuhong","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7426-6248","authenticated-orcid":false,"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-9797","authenticated-orcid":false,"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2025. GUROBI. https:\/\/docs.gurobi.com\/projects\/optimizer\/en\/current\/index.html"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_3_2_1_3_1","volume-title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=lJWUJWLCJo","author":"Bertsch Amanda","unstructured":"Amanda Bertsch, Uri Alon, Graham Neubig, and Matthew R. Gormley. 2023. Unlimiformer: Long-Range Transformers with Unlimited Length Input. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=lJWUJWLCJo"},{"key":"e_1_3_2_1_4_1","volume-title":"Striped Attention: Faster Ring Attention for Causal Transformers. arXiv:2311.09431 [cs.LG] https:\/\/arxiv.org\/abs\/2311.09431","author":"Brandon William","year":"2023","unstructured":"William Brandon, Aniruddha Nrusimha, Kevin Qian, Zachary Ankner, Tian Jin, Zhiye Song, and Jonathan Ragan-Kelley. 2023. Striped Attention: Faster Ring Attention for Causal Transformers. arXiv:2311.09431 [cs.LG] https:\/\/arxiv.org\/abs\/2311.09431"},{"key":"e_1_3_2_1_5_1","volume-title":"Language Models are Few-Shot Learners. CoRR abs\/2005.14165","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. CoRR abs\/2005.14165 (2020). arXiv:2005.14165 https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651379"},{"key":"e_1_3_2_1_7_1","volume-title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing. arXiv:2411.05735 [cs.LG] https:\/\/arxiv.org\/abs\/2411.05735","author":"Chen Mayee F.","year":"2025","unstructured":"Mayee F. Chen, Michael Y. Hu, Nicholas Lourie, Kyunghyun Cho, and Christopher R\u00e9. 2025. Aioli: A Unified Optimization Framework for Language Model Data Mixing. arXiv:2411.05735 [cs.LG] https:\/\/arxiv.org\/abs\/2411.05735"},{"key":"e_1_3_2_1_8_1","unstructured":"Tiancheng Chen Ales Kubicek Langwen Huang and Torsten Hoefler. 2025. CrossPipe: Towards Optimal Pipeline Schedules for Cross-Datacenter Training. arXiv:2507.00217 [cs.DC] https:\/\/arxiv.org\/abs\/2507.00217"},{"key":"e_1_3_2_1_9_1","volume-title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=wCXAlfvCy6","author":"Chen Yukang","year":"2025","unstructured":"Yukang Chen, Fuzhao Xue, Dacheng Li, Qinghao Hu, Ligeng Zhu, Xiuyu Li, Yunhao Fang, Haotian Tang, Shang Yang, Zhijian Liu, Yihui He, Hongxu Yin, Pavlo Molchanov, Jan Kautz, Linxi Fan, Yuke Zhu, Yao Lu, and Song Han. 2025. LongVILA: Scaling Long-Context Visual Language Models for Long Videos. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=wCXAlfvCy6"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Tri Dao Daniel Y. Fu Stefano Ermon Atri Rudra and Christopher R\u00e9. 2022. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. arXiv:2205.14135 [cs.LG] https:\/\/arxiv.org\/abs\/2205.14135","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_2_1_11_1","unstructured":"DeepSeek-AI. 2024. DeepSeek-V2: A Strong Economical and Efficient Mixture-of-Experts Language Model. arXiv:2405.04434 [cs.CL] https:\/\/arxiv.org\/abs\/2405.04434"},{"key":"e_1_3_2_1_12_1","unstructured":"DeepSeek-AI. 2025. DeepSeek-V3 Technical Report. arXiv:2412.19437 [cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_2_1_13_1","volume-title":"Levine (Eds.)","volume":"36","author":"Dehghani Mostafa","year":"2023","unstructured":"Mostafa Dehghani, Basil Mustafa, Josip Djolonga, Jonathan Heek, Matthias Minderer, Mathilde Caron, Andreas Steiner, Joan Puigcerver, Robert Geirhos, Ibrahim M Alabdulmohsin, Avital Oliver, Piotr Padlewski, Alexey Gritsenko, Mario Lucic, and Neil Houlsby. 2023. Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 2252\u20132274. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/06ea400b9b7cfce6428ec27a371632eb-Paper-Conference.pdf"},{"key":"e_1_3_2_1_14_1","unstructured":"Hantian Ding Zijian Wang Giovanni Paolini Varun Kumar Anoop Deoras Dan Roth and Stefano Soatto. 2024. Fewer Truncations Improve Language Modeling. arXiv:2404.10830 [cs.CL] https:\/\/arxiv.org\/abs\/2404.10830"},{"key":"e_1_3_2_1_15_1","unstructured":"Mahidhar Dwarampudi and N V Subba Reddy. 2019. Effects of padding on LSTMs and CNNs. arXiv:1903.07288 [cs.LG] https:\/\/arxiv.org\/abs\/1903.07288"},{"key":"e_1_3_2_1_16_1","volume-title":"USP: A Unified Sequence Parallelism Approach for Long Context Generative AI. arXiv:2405.07719 [cs.LG] https:\/\/arxiv.org\/abs\/2405.07719","author":"Fang Jiarui","year":"2024","unstructured":"Jiarui Fang and Shangchun Zhao. 2024. USP: A Unified Sequence Parallelism Approach for Long Context Generative AI. arXiv:2405.07719 [cs.LG] https:\/\/arxiv.org\/abs\/2405.07719"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3692634"},{"key":"e_1_3_2_1_18_1","unstructured":"Tianyu Gao Alexander Wettig Howard Yen and Danqi Chen. 2025. How to Train Long-Context Language Models (Effectively). arXiv:2410.02660 [cs.CL] https:\/\/arxiv.org\/abs\/2410.02660"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Hao Ge Junda Feng Qi Huang Fangcheng Fu Xiaonan Nie Lei Zuo Haibin Lin Bin Cui and Xin Liu. 2025. ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12 000 GPUs. arXiv:2502.21231 [cs.DC] https:\/\/arxiv.org\/abs\/2502.21231","DOI":"10.1145\/3718958.3754352"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695969"},{"key":"e_1_3_2_1_21_1","unstructured":"Google. 2025. Gemini 2.5: Our most intelligent AI model. https:\/\/blog.google\/technology\/google-deepmind\/gemini-model-thinking-updates-march-2025\/#gemini-2-5-thinking"},{"key":"e_1_3_2_1_22_1","unstructured":"Priya Goyal Piotr Doll\u00e1r Ross Girshick Pieter Noordhuis Lukasz Wesolowski Aapo Kyrola Andrew Tulloch Yangqing Jia and Kaiming He. 2018. Accurate Large Minibatch SGD: Training ImageNet in 1 Hour. arXiv:1706.02677 [cs.CV] https:\/\/arxiv.org\/abs\/1706.02677"},{"key":"e_1_3_2_1_23_1","unstructured":"Diandian Gu Peng Sun Qinghao Hu Ting Huang Xun Chen Yingtong Xiong Guoteng Wang Qiaoling Chen Shangchun Zhao Jiarui Fang Yonggang Wen Tianwei Zhang Xin Jin and Xuanzhe Liu. 2024. Loong-Train: Efficient Training of Long-Sequence LLMs with Head-Context Parallelism. arXiv:2406.18485 [cs.DC] https:\/\/arxiv.org\/abs\/2406.18485"},{"key":"e_1_3_2_1_24_1","unstructured":"Aaron Harlap Deepak Narayanan Amar Phanishayee Vivek Seshadri Nikhil Devanur Greg Ganger and Phil Gibbons. 2018. PipeDream: Fast and Efficient Pipeline Parallel DNN Training. arXiv:1806.03377 [cs.DC] https:\/\/arxiv.org\/abs\/1806.03377"},{"key":"e_1_3_2_1_25_1","unstructured":"huggingface. 2025. Padding and truncation. https:\/\/huggingface.co\/docs\/transformers\/pad_truncation"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3662158.3662806"},{"key":"e_1_3_2_1_27_1","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. arXiv:2402.15627 [cs.LG] https:\/\/arxiv.org\/abs\/2402.15627"},{"key":"e_1_3_2_1_28_1","volume-title":"Jia Li, Chenghao Mou, Carlos Mu\u00f1oz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, Dzmitry Bahdanau, Leandro von Werra, and Harm de Vries.","author":"Kocetkov Denis","year":"2022","unstructured":"Denis Kocetkov, Raymond Li, Loubna Ben Allal, Jia Li, Chenghao Mou, Carlos Mu\u00f1oz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, Dzmitry Bahdanau, Leandro von Werra, and Harm de Vries. 2022. The Stack: 3 TB of permissively licensed source code. arXiv:2211.15533 [cs.CL] https:\/\/arxiv.org\/abs\/2211.15533"},{"key":"e_1_3_2_1_29_1","unstructured":"Vijay Korthikanti Jared Casper Sangkug Lym Lawrence McAfee Michael Andersch Mohammad Shoeybi and Bryan Catanzaro. 2022. Reducing Activation Recomputation in Large Transformer Models. arXiv:2205.05198 [cs.LG] https:\/\/arxiv.org\/abs\/2205.05198"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.818"},{"key":"e_1_3_2_1_31_1","volume-title":"DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training. arXiv:2310.03294 [cs.LG] https:\/\/arxiv.org\/abs\/2310.03294","author":"Li Dacheng","year":"2024","unstructured":"Dacheng Li, Rulin Shao, Anze Xie, Eric P. Xing, Xuezhe Ma, Ion Stoica, Joseph E. Gonzalez, and Hao Zhang. 2024. DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training. arXiv:2310.03294 [cs.LG] https:\/\/arxiv.org\/abs\/2310.03294"},{"key":"e_1_3_2_1_32_1","unstructured":"Hao Liu Matei Zaharia and Pieter Abbeel. 2023. Ring Attention with Blockwise Transformers for Near-Infinite Context. arXiv:2310.01889 [cs.CL] https:\/\/arxiv.org\/abs\/2310.01889"},{"key":"e_1_3_2_1_33_1","unstructured":"Meta. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv:2307.09288 [cs.CL] https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_1_34_1","unstructured":"Meta. 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_36_1","unstructured":"NVIDIA. 2022. NVIDIA Collective Communication Library (NCCL) Documentation. https:\/\/docs.nvidia.com\/deeplearning\/nccl\/user-guide\/docs\/index.html."},{"key":"e_1_3_2_1_37_1","unstructured":"NVIDIA. 2025. DGX A100 System Topology. https:\/\/docs.nvidia.com\/dgx\/dgxa100-user-guide\/introduction-to-dgxa100.html"},{"key":"e_1_3_2_1_38_1","unstructured":"NVIDIA. 2025. DGX H100\/200 System Topology. https:\/\/docs.nvidia.com\/dgx\/dgxh100-user-guide\/"},{"key":"e_1_3_2_1_39_1","unstructured":"NVIDIA. 2025. TransformerEngine. https:\/\/github.com\/NVIDIA\/TransformerEngine"},{"key":"e_1_3_2_1_40_1","volume-title":"Zhangir Azerbayev, and Jimmy Ba.","author":"Paster Keiran","year":"2023","unstructured":"Keiran Paster, Marco Dos Santos, Zhangir Azerbayev, and Jimmy Ba. 2023. OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text. arXiv:2310.06786 [cs.AI] https:\/\/arxiv.org\/abs\/2310.06786"},{"key":"e_1_3_2_1_41_1","volume-title":"Anton Lozhkov, Margaret Mitchell, Colin Raffel, Leandro Von Werra, and Thomas Wolf.","author":"Penedo Guilherme","year":"2024","unstructured":"Guilherme Penedo, Hynek Kydl\u00ed\u010dek, Loubna Ben allal, Anton Lozhkov, Margaret Mitchell, Colin Raffel, Leandro Von Werra, and Thomas Wolf. 2024. The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale. arXiv:2406.17557 [cs.CL] https:\/\/arxiv.org\/abs\/2406.17557"},{"key":"e_1_3_2_1_42_1","volume-title":"Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar, and Oncel Tuzel.","author":"Pouransari Hadi","year":"2024","unstructured":"Hadi Pouransari, Chun-Liang Li, Jen-Hao Rick Chang, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar, and Oncel Tuzel. 2024. Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum. In Advances in Neural Information Processing Systems, A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Eds.), Vol. 37. Curran Associates, Inc., 36121\u201336147. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/3f9bf45ea04c98ad7cb857f951f499e2-Paper-Conference.pdf"},{"key":"e_1_3_2_1_43_1","unstructured":"Penghui Qi Xinyi Wan Guangxing Huang and Min Lin. 2023. Zero Bubble Pipeline Parallelism. arXiv:2401.10241 [cs.DC] https:\/\/arxiv.org\/abs\/2401.10241"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Samyam Rajbhandari Jeff Rasley Olatunji Ruwase and Yuxiong He. 2020. ZeRO: Memory Optimizations Toward Training Trillion Parameter Models. arXiv:1910.02054 [cs.LG] https:\/\/arxiv.org\/abs\/1910.02054","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_46_1","unstructured":"Zhiqiang Shen Tianhua Tao Liqun Ma Willie Neiswanger Zhengzhong Liu Hongyi Wang Bowen Tan Joel Hestness Natalia Vassilieva Daria Soboleva and Eric Xing. 2024. SlimPajama-DC: Understanding Data Combinations for LLM Training. arXiv:2309.10818 [cs.CL] https:\/\/arxiv.org\/abs\/2309.10818"},{"key":"e_1_3_2_1_47_1","volume-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. CoRR abs\/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 Multi-Billion Parameter Language Models Using Model Parallelism. CoRR abs\/1909.08053 (2019). arXiv:1909.08053 http:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_2_1_48_1","volume-title":"Le","author":"Smith Samuel L.","year":"2018","unstructured":"Samuel L. Smith, Pieter-Jan Kindermans, Chris Ying, and Quoc V. Le. 2018. Don't Decay the Learning Rate, Increase the Batch Size. arXiv:1711.00489 [cs.LG] https:\/\/arxiv.org\/abs\/1711.00489"},{"key":"e_1_3_2_1_49_1","unstructured":"Qwen Team. 2024. Qwen2 Technical Report. arXiv:2407.10671 [cs.CL] https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_2_1_50_1","unstructured":"Qwen Team. 2025. Qwen2.5 Technical Report. arXiv:2412.15115 [cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_1_51_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715998"},{"key":"e_1_3_2_1_53_1","unstructured":"Zheng Wang Anna Cai Xinfeng Xie Zaifeng Pan Yue Guan Weiwei Chu Jie Wang Shikai Li Jianyu Huang Chris Cai Yuchen Hao and Yufei Ding. 2025. WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Training. arXiv:2503.17924 [cs.DC] https:\/\/arxiv.org\/abs\/2503.17924"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.260"},{"key":"e_1_3_2_1_55_1","unstructured":"Yang You Igor Gitman and Boris Ginsburg. 2017. Large Batch Training of Convolutional Networks. arXiv:1708.03888 [cs.CV] https:\/\/arxiv.org\/abs\/1708.03888"},{"key":"e_1_3_2_1_56_1","unstructured":"Yang You Jing Li Sashank Reddi Jonathan Hseu Sanjiv Kumar Srinadh Bhojanapalli Xiaodan Song James Demmel Kurt Keutzer and Cho-Jui Hsieh. 2020. Large Batch Optimization for Deep Learning: Training BERT in 76 minutes. arXiv:1904.00962 [cs.LG] https:\/\/arxiv.org\/abs\/1904.00962"},{"key":"e_1_3_2_1_57_1","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Yuan Tailing","year":"2024","unstructured":"Tailing Yuan, Yuliang Liu, Xucheng Ye, Shenglong Zhang, Jianchao Tan, Bin Chen, Chengru Song, and Di Zhang. 2024. Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Parallelism. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, CA, 545\u2013561. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/yuan"},{"key":"e_1_3_2_1_58_1","unstructured":"Liang Zhao Tianwen Wei Liang Zeng Cheng Cheng Liu Yang Peng Cheng Lijie Wang Chenxia Li Xuejie Wu Bo Zhu Yimeng Gan Rui Hu Shuicheng Yan Han Fang and Yahui Zhou. 2024. LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models. arXiv:2406.00605 [cs.CL] https:\/\/arxiv.org\/abs\/2406.00605"}],"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\/3767295.3769369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:17:43Z","timestamp":1780661863000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3769369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":58,"alternative-id":["10.1145\/3767295.3769369","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3769369","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"}}]}}