{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T05:12:26Z","timestamp":1783746746295,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"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":[[2026,7,13]]},"DOI":"10.1145\/3806645.3807581","type":"proceedings-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:21:11Z","timestamp":1783743671000},"page":"152-164","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1511-1323","authenticated-orcid":false,"given":"Yuyang","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8654-0192","authenticated-orcid":false,"given":"Runxin","family":"Zhong","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7828-9030","authenticated-orcid":false,"given":"Zan","family":"Zong","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1986-1799","authenticated-orcid":false,"given":"Hengjie","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2358-3395","authenticated-orcid":false,"given":"Yuyang","family":"Jin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7656-6428","authenticated-orcid":false,"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"Video generation models as world simulators","author":"Brooks Tim","year":"2024","unstructured":"Tim Brooks, Bill Peebles, Connor Holmes, Amos Storkey, Alexei\u00a0A. Efros, Andreas Terzis, Abhinav Gupta, Devi Parikh, Douwe Kiela, Gabriel Synnaeve, Hannaneh Hajishirzi, Ilya Sutskever, James Zung, Joelle Pineau, Luke Metz, Mira Murati, Pranav Shyam, Rohun Kulkarni, Ruth Fong, Vedant Misra, Yufei Guo, Adri\u00e0 Recasens, Alexander Papiez, Alexandre Lebrun, Arthur Mensch, Avel Gu\u00e9nin, Bowen Baker, Brandon Houghton, Brian Tanner, Briane Paul\u00a0V. Samson, Chang Chen, Christopher Clark, Cory McLean, David Martinez-Rubio, David Schnurr, Desu Narendra, Eli Moser, Ethan Perez, Igor Mordatch, J.R. Harris, Joey Faulkner, John Baumgartner, Karl Cobbe, Liam Fedus, Madeleine Thompson, Mark Chen, Mayur Mudigonda, Mimee Xu, Noemi Dreymann, Teddy Lee, Theresa Yoon, Timothy Lillicrap, Torrey Fellbaum, Trevor Darrell, Yuntao Bai, and Yutian Chen. 2024. Video generation models as world simulators. Technical Report. OpenAI. https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"e_1_3_3_2_3_2","unstructured":"Pengtao Chen Mingzhu Shen Peng Ye Jianjian Cao Chongjun Tu Christos-Savvas Bouganis Yiren Zhao and Tao Chen. 2024. Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers. arxiv:https:\/\/arXiv.org\/abs\/2406.01125\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2406.01125"},{"key":"e_1_3_3_2_4_2","unstructured":"Yuyang Chen Linqian Zeng Yijin ZHou Hengjie Li and Jidong Zhai. 2026. Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness. arxiv:https:\/\/arXiv.org\/abs\/2603.00519\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2603.00519"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3015"},{"key":"e_1_3_3_2_6_2","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Dao Tri","year":"2024","unstructured":"Tri Dao. 2024. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=mZn2Xyh9Ec"},{"key":"e_1_3_3_2_7_2","unstructured":"vipshop.com DefTruth. 2025. cache-dit: A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.https:\/\/github.com\/vipshop\/cache-dit.git Open-source software available at https:\/\/github.com\/vipshop\/cache-dit.git."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Jiarui Fang Jinzhe Pan Xibo Sun Aoyu Li and Jiannan Wang. 2024. xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism. CoRR abs\/2411.01738 (2024). 10.48550\/ARXIV.2411.01738 arXiv:https:\/\/arXiv.org\/abs\/2411.01738","DOI":"10.48550\/ARXIV.2411.01738"},{"key":"e_1_3_3_2_9_2","unstructured":"Jiarui Fang and Shangchun Zhao. 2024. A Unified Sequence Parallelism Approach for Long Context Generative AI. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.07719 (2024)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. CoRR abs\/2207.12598 (2022). 10.48550\/ARXIV.2207.12598 arXiv:https:\/\/arXiv.org\/abs\/2207.12598","DOI":"10.48550\/ARXIV.2207.12598"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Sam\u00a0Ade Jacobs Masahiro Tanaka Chengming Zhang Minjia Zhang Shuaiwen\u00a0Leon Song Samyam Rajbhandari and Yuxiong He. 2023. DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models. CoRR abs\/2309.14509 (2023). 10.48550\/ARXIV.2309.14509 arXiv:https:\/\/arXiv.org\/abs\/2309.14509","DOI":"10.48550\/ARXIV.2309.14509"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Weijie Kong Qi Tian Zijian Zhang Rox Min Zuozhuo Dai Jin Zhou Jiangfeng Xiong Xin Li Bo Wu Jianwei Zhang Kathrina Wu Qin Lin Junkun Yuan Yanxin Long Aladdin Wang Andong Wang Changlin Li Duojun Huang Fang Yang Hao Tan Hongmei Wang Jacob Song Jiawang Bai Jianbing Wu Jinbao Xue Joey Wang Kai Wang Mengyang Liu Pengyu Li Shuai Li Weiyan Wang Wenqing Yu Xinchi Deng Yang Li Yi Chen Yutao Cui Yuanbo Peng Zhentao Yu Zhiyu He Zhiyong Xu Zixiang Zhou Zunnan Xu Yangyu Tao Qinglin Lu Songtao Liu Daquan Zhou Hongfa Wang Yong Yang Di Wang Yuhong Liu Jie Jiang and Caesar Zhong. 2024. HunyuanVideo: A Systematic Framework For Large Video Generative Models. CoRR abs\/2412.03603 (2024). 10.48550\/ARXIV.2412.03603 arXiv:https:\/\/arXiv.org\/abs\/2412.03603","DOI":"10.48550\/ARXIV.2412.03603"},{"key":"e_1_3_3_2_14_2","unstructured":"Kuaishou Technology. 2025. Kling - Community for short video & livestream. https:\/\/kling.kuaishou.com\/en Accessed: 2025-03-07."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00686"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Feng Liu Shiwei Zhang Xiaofeng Wang Yujie Wei Haonan Qiu Yuzhong Zhao Yingya Zhang Qixiang Ye and Fang Wan. 2024. Timestep Embedding Tells: It\u2019s Time to Cache for Video Diffusion Model. CoRR abs\/2411.19108 (2024). 10.48550\/ARXIV.2411.19108 arXiv:https:\/\/arXiv.org\/abs\/2411.19108","DOI":"10.48550\/ARXIV.2411.19108"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0386"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Hao Liu Matei Zaharia and Pieter Abbeel. 2023. Ring Attention with Blockwise Transformers for Near-Infinite Context. CoRR abs\/2310.01889 (2023). 10.48550\/ARXIV.2310.01889 arXiv:https:\/\/arXiv.org\/abs\/2310.01889","DOI":"10.48550\/ARXIV.2310.01889"},{"key":"e_1_3_3_2_19_2","unstructured":"Jiacheng Liu Chang Zou Yuanhuiyi Lyu Junjie Chen and Linfeng Zhang. 2025. From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.06923 (2025)."},{"key":"e_1_3_3_2_20_2","unstructured":"Qiang Liu. 2022. Rectified Flow: A Marginal Preserving Approach to Optimal Transport. arxiv:https:\/\/arXiv.org\/abs\/2209.14577\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/2209.14577"},{"key":"e_1_3_3_2_21_2","unstructured":"Guoqing Ma Haoyang Huang Kun Yan Liangyu Chen Nan Duan Shengming Yin Changyi Wan Ranchen Ming Xiaoniu Song Xing Chen Yu Zhou Deshan Sun Deyu Zhou Jian Zhou Kaijun Tan Kang An Mei Chen Wei Ji Qiling Wu Wen Sun Xin Han Yanan Wei Zheng Ge Aojie Li Bin Wang Bizhu Huang Bo Wang Brian Li Changxing Miao Chen Xu Chenfei Wu Chenguang Yu Dapeng Shi Dingyuan Hu Enle Liu Gang Yu Ge Yang Guanzhe Huang Gulin Yan Haiyang Feng Hao Nie Haonan Jia Hanpeng Hu Hanqi Chen Haolong Yan Heng Wang Hongcheng Guo Huilin Xiong Huixin Xiong Jiahao Gong Jianchang Wu Jiaoren Wu Jie Wu Jie Yang Jiashuai Liu Jiashuo Li Jingyang Zhang Junjing Guo Junzhe Lin Kaixiang Li Lei Liu Lei Xia Liang Zhao Liguo Tan Liwen Huang Liying Shi Ming Li Mingliang Li Muhua Cheng Na Wang Qiaohui Chen Qinglin He Qiuyan Liang Quan Sun Ran Sun Rui Wang Shaoliang Pang Shiliang Yang Sitong Liu Siqi Liu Shuli Gao Tiancheng Cao Tianyu Wang Weipeng Ming Wenqing He Xu Zhao Xuelin Zhang Xianfang Zeng Xiaojia Liu Xuan Yang Yaqi Dai Yanbo Yu Yang Li Yineng Deng Yingming Wang Yilei Wang Yuanwei Lu Yu Chen Yu Luo Yuchu Luo Yuhe Yin Yuheng Feng Yuxiang Yang Zecheng Tang Zekai Zhang Zidong Yang Binxing Jiao Jiansheng Chen Jing Li Shuchang Zhou Xiangyu Zhang Xinhao Zhang Yibo Zhu Heung-Yeung Shum and Daxin Jiang. 2025. Step-Video-T2V Technical Report: The Practice Challenges and Future of Video Foundation Model. arxiv:https:\/\/arXiv.org\/abs\/2502.10248\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2502.10248"},{"key":"e_1_3_3_2_22_2","unstructured":"Xinyin Ma Gongfan Fang Michael\u00a0Bi Mi and Xinchao Wang. 2024. Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching. arxiv:https:\/\/arXiv.org\/abs\/2406.01733\u00a0[cs.LG]"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Chenlin Meng Robin Rombach Ruiqi Gao Diederik\u00a0P. Kingma Stefano Ermon Jonathan Ho and Tim Salimans. 2022. On Distillation of Guided Diffusion Models. arXiv e-prints Article arXiv:2210.03142 (Oct. 2022) arXiv:2210.03142\u00a0pages. 10.48550\/arXiv.2210.03142 arxiv:https:\/\/arXiv.org\/abs\/2210.03142\u00a0[cs.CV]","DOI":"10.48550\/arXiv.2210.03142"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_2_25_2","unstructured":"Axel Sauer Dominik Lorenz Andreas Blattmann and Robin Rombach. 2023. Adversarial Diffusion Distillation. arxiv:https:\/\/arXiv.org\/abs\/2311.17042\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2311.17042"},{"key":"e_1_3_3_2_26_2","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:https:\/\/arXiv.org\/abs\/1909.08053http:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_3_2_27_2","unstructured":"Genmo Team. 2024. Mochi 1. https:\/\/github.com\/genmoai\/models."},{"key":"e_1_3_3_2_28_2","unstructured":"VideoSys Team. 2024. VideoSys: An Easy and Efficient System for Video Generation. https:\/\/github.com\/NUS-HPC-AI-Lab\/VideoSys"},{"key":"e_1_3_3_2_29_2","unstructured":"Team Wan Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang Jianyuan Zeng Jiayu Wang Jingfeng Zhang Jingren Zhou Jinkai Wang Jixuan Chen Kai Zhu Kang Zhao Keyu Yan Lianghua Huang Mengyang Feng Ningyi Zhang Pandeng Li Pingyu Wu Ruihang Chu Ruili Feng Shiwei Zhang Siyang Sun Tao Fang Tianxing Wang Tianyi Gui Tingyu Weng Tong Shen Wei Lin Wei Wang Wei Wang Wenmeng Zhou Wente Wang Wenting Shen Wenyuan Yu Xianzhong Shi Xiaoming Huang Xin Xu Yan Kou Yangyu Lv Yifei Li Yijing Liu Yiming Wang Yingya Zhang Yitong Huang Yong Li You Wu Yu Liu Yulin Pan Yun Zheng Yuntao Hong Yupeng Shi Yutong Feng Zeyinzi Jiang Zhen Han Zhi-Fan Wu and Ziyu Liu. 2025. Wan: Open and Advanced Large-Scale Video Generative Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20314 (2025)."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Jiannan Wang Jiarui Fang Aoyu Li and PengCheng Yang. 2024. PipeFusion: Displaced Patch Pipeline Parallelism for Inference of Diffusion Transformer Models. CoRR abs\/2405.14430 (2024). 10.48550\/ARXIV.2405.14430 arXiv:https:\/\/arXiv.org\/abs\/2405.14430","DOI":"10.48550\/ARXIV.2405.14430"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Haocheng Xi Shuo Yang Yilong Zhao Chenfeng Xu Muyang Li Xiuyu Li Yujun Lin Han Cai Jintao Zhang Dacheng Li Jianfei Chen Ion Stoica Kurt Keutzer and Song Han. 2025. Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity. CoRR abs\/2502.01776 (2025). 10.48550\/ARXIV.2502.01776 arXiv:https:\/\/arXiv.org\/abs\/2502.01776","DOI":"10.48550\/ARXIV.2502.01776"},{"key":"e_1_3_3_2_32_2","unstructured":"Shuo Yang Haocheng Xi Yilong Zhao Muyang Li Jintao Zhang Han Cai Yujun Lin Xiuyu Li Chenfeng Xu Kelly Peng et\u00a0al. 2025. Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.18875 (2025)."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng Da Yin Xiaotao Gu Yuxuan Zhang Weihan Wang Yean Cheng Ting Liu Bin Xu Yuxiao Dong and Jie Tang. 2024. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. CoRR abs\/2408.06072 (2024). 10.48550\/ARXIV.2408.06072 arXiv:https:\/\/arXiv.org\/abs\/2408.06072","DOI":"10.48550\/ARXIV.2408.06072"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Zihao Ye Lequn Chen Ruihang Lai Wuwei Lin Yineng Zhang Stephanie Wang Tianqi Chen Baris Kasikci Vinod Grover Arvind Krishnamurthy and Luis Ceze. 2025. FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving. CoRR abs\/2501.01005 (2025). 10.48550\/ARXIV.2501.01005 arXiv:https:\/\/arXiv.org\/abs\/2501.01005","DOI":"10.48550\/ARXIV.2501.01005"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0037"},{"key":"e_1_3_3_2_36_2","volume-title":"International Conference on Machine Learning (ICML)","author":"Zhang Jintao","year":"2025","unstructured":"Jintao Zhang, Haofeng Huang, Pengle Zhang, Jia Wei, Jun Zhu, and Jianfei Chen. 2025. Sageattention2: Efficient attention with thorough outlier smoothing and per-thread int4 quantization. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_2_37_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhang Jintao","year":"2025","unstructured":"Jintao Zhang, Jia Wei, Pengle Zhang, Jun Zhu, and Jianfei Chen. 2025. SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Xuanlei Zhao Shenggan Cheng Zangwei Zheng Zheming Yang Ziming Liu and Yang You. 2024. DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers. CoRR abs\/2403.10266 (2024). 10.48550\/ARXIV.2403.10266 arXiv:https:\/\/arXiv.org\/abs\/2403.10266","DOI":"10.48550\/ARXIV.2403.10266"},{"key":"e_1_3_3_2_39_2","unstructured":"Xuanlei Zhao Xiaolong Jin Kai Wang and Yang You. 2024. Real-Time Video Generation with Pyramid Attention Broadcast. arxiv:https:\/\/arXiv.org\/abs\/2408.12588\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2408.12588"},{"key":"e_1_3_3_2_40_2","unstructured":"Lianmin Zheng Liangsheng Yin Zhiqiang Xie Chuyue Sun Jeff Huang Cody\u00a0Hao Yu Shiyi Cao Christos Kozyrakis Ion Stoica Joseph\u00a0E. Gonzalez Clark Barrett and Ying Sheng. 2024. SGLang: Efficient Execution of Structured Language Model Programs. arxiv:https:\/\/arXiv.org\/abs\/2312.07104\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2312.07104"}],"event":{"name":"HPDC '26: 35th International Symposium on High-Performance Parallel and Distributed Computing","location":"Cleveland USA","acronym":"HPDC '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:24:44Z","timestamp":1783743884000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3806645.3807581"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":39,"alternative-id":["10.1145\/3806645.3807581","10.1145\/3806645"],"URL":"https:\/\/doi.org\/10.1145\/3806645.3807581","relation":{},"subject":[],"published":{"date-parts":[[2026,7,13]]},"assertion":[{"value":"2026-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}