{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:28:13Z","timestamp":1786476493824,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62272122"],"award-info":[{"award-number":["62272122"]}]},{"name":"Hong Kong CRF grants","award":["C7004-22G"],"award-info":[{"award-number":["C7004-22G"]}]},{"name":"Hong Kong CRF grants","award":["C6015-23G"],"award-info":[{"award-number":["C6015-23G"]}]},{"name":"Shenzhen Science and Technology Program","award":["KJZD20240903104103005"],"award-info":[{"award-number":["KJZD20240903104103005"]}]},{"name":"Shenzhen Science and Technology Program","award":["KJZD20230923115113026"],"award-info":[{"award-number":["KJZD20230923115113026"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3829204","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"207-221","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5147-0844","authenticated-orcid":false,"given":"Wenxiang","family":"Lin","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1172-9935","authenticated-orcid":false,"given":"Xinglin","family":"Pan","sequence":"additional","affiliation":[{"name":"Data Science and Analytics Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7492-2069","authenticated-orcid":false,"given":"Ruibo","family":"Fan","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1418-5160","authenticated-orcid":false,"given":"Shaohuai","family":"Shi","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9745-4372","authenticated-orcid":false,"given":"Xiaowen","family":"Chu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00051"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00080"},{"key":"e_1_3_2_1_3_1","volume-title":"Advances in Neural Information Processing Systems","volume":"25","author":"Dean Jeffrey","year":"2012","unstructured":"Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Marc' aurelio Ranzato, Andrew Senior, Paul Tucker, Ke Yang, Quoc Le, and Andrew Ng. 2012. Large Scale Distributed Deep Networks. In Advances in Neural Information Processing Systems, Vol. 25. Curran Associates, Inc."},{"key":"e_1_3_2_1_4_1","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai Daya Guo Dejian Yang Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fucong Dai Fuli Luo Guangbo Hao Guanting Chen Guowei Li H. Zhang Han Bao Hanwei Xu Haocheng Wang Haowei Zhang Honghui Ding Huajian Xin Huazuo Gao Hui Li Hui Qu J. L. Cai Jian Liang Jianzhong Guo Jiaqi Ni Jiashi Li Jiawei Wang Jin Chen Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li Junxiao Song Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Lei Xu Leyi Xia Liang Zhao Litong Wang Liyue Zhang Meng Li Miaojun Wang Mingchuan Zhang Minghua Zhang Minghui Tang Mingming Li Ning Tian Panpan Huang Peiyi Wang Peng Zhang Qiancheng Wang Qihao Zhu Qinyu Chen Qiushi Du R. J. Chen R. L. Jin Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang Runxin Xu Ruoyu Zhang Ruyi Chen S. S. Li Shanghao Lu Shangyan Zhou Shanhuang Chen Shaoqing Wu Shengfeng Ye Shengfeng Ye Shirong Ma Shiyu Wang Shuang Zhou Shuiping Yu Shunfeng Zhou Shuting Pan T. Wang Tao Yun Tian Pei Tianyu Sun W. L. Xiao Wangding Zeng Wanjia Zhao Wei An Wen Liu Wenfeng Liang Wenjun Gao Wenqin Yu Wentao Zhang X. Q. Li Xiangyue Jin Xianzu Wang Xiao Bi Xiaodong Liu Xiaohan Wang Xiaojin Shen Xiaokang Chen Xiaokang Zhang Xiaosha Chen Xiaotao Nie Xiaowen Sun Xiaoxiang Wang Xin Cheng Xin Liu Xin Xie Xingchao Liu Xingkai Yu Xinnan Song Xinxia Shan Xinyi Zhou Xinyu Yang Xinyuan Li Xuecheng Su Xuheng Lin Y. K. Li Y. Q. Wang Y. X. Wei Y. X. Zhu Yang Zhang Yanhong Xu Yanhong Xu Yanping Huang Yao Li Yao Zhao Yaofeng Sun Yaohui Li Yaohui Wang Yi Yu Yi Zheng Yichao Zhang Yifan Shi Yiliang Xiong Ying He Ying Tang Yishi Piao Yisong Wang Yixuan Tan Yiyang Ma Yiyuan Liu Yongqiang Guo Yu Wu Yuan Ou Yuchen Zhu Yuduan Wang Yue Gong Yuheng Zou Yujia He Yukun Zha Yunfan Xiong Yunxian Ma Yuting Yan Yuxiang Luo Yuxiang You Yuxuan Liu Yuyang Zhou Z. F. Wu Z. Z. Ren Zehui Ren Zhangli Sha Zhe Fu Zhean Xu Zhen Huang Zhen Zhang Zhenda Xie Zhengyan Zhang Zhewen Hao Zhibin Gou Zhicheng Ma Zhigang Yan Zhihong Shao Zhipeng Xu Zhiyu Wu Zhongyu Zhang Zhuoshu Li Zihui Gu Zijia Zhu Zijun Liu Zilin Li Ziwei Xie Ziyang Song Ziyi Gao and ZizhengPan. 2025. DeepSeek-V3 Technical Report. arXiv:2412.19437 [cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Tim Dettmers Artidoro Pagnoni Ari Holtzman and Luke Zettlemoyer. 2023. QLoRA: Efficient Finetuning of Quantized LLMs. In NeurIPS.","DOI":"10.52202\/075280-0441"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/PCS.2015.7170048"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2005.6"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS '26)","author":"Fan Ruibo","year":"2026","unstructured":"Ruibo Fan, Xiangrui Yu, Xinglin Pan, Zeyu Li, Weile Luo, Qiang Wang, Wei Wang, and Xiaowen Chu. 2026. ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression. In Proceedings of the ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS '26)."},{"key":"e_1_3_2_1_9_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey et al. 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_10_1","volume-title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks. CoRR abs\/2410.20650","author":"Hao Yongchang","year":"2024","unstructured":"Yongchang Hao, Yanshuai Cao, and Lili Mou. 2024. NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks. CoRR abs\/2410.20650 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"ZipNN: Lossless Compression for AI Models. CoRR abs\/2411.05239","author":"Hershcovitch Moshik","year":"2024","unstructured":"Moshik Hershcovitch, Andrew Wood, Leshem Choshen, Guy Girmonsky, Roy Leibovitz, Ilias Ennmouri, Michal Malka, Peter Chin, Swaminathan Sundararaman, and Danny Harnik. 2024. ZipNN: Lossless Compression for AI Models. CoRR abs\/2411.05239 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of Machine Learning and Systems, D. Song, M. Carbin, and T. Chen (Eds.)","volume":"5","author":"Hwang Changho","year":"2023","unstructured":"Changho Hwang, Wei Cui, Yifan Xiong, Ziyue Yang, Ze Liu, Han Hu, Zilong Wang, Rafael Salas, Jithin Jose, Prabhat Ram, HoYuen Chau, Peng Cheng, Fan Yang, Mao Yang, and Yongqiang Xiong. 2023. Tutel: Adaptive Mixture-of-Experts at Scale. In Proceedings of Machine Learning and Systems, D. Song, M. Carbin, and T. Chen (Eds.), Vol. 5. Curan, 269\u2013287. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/file\/5616d34cf8ff73942cfd5aa922842556-Paper-mlsys2023.pdf"},{"key":"e_1_3_2_1_14_1","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra Singh Chaplot Diego de las Casas Emma Bou Hanna Florian Bressand Gianna Lengyel Guillaume Bour Guillaume Lample L\u00e9lio Renard Lavaud Lucile Saulnier Marie-Anne Lachaux Pierre Stock Sandeep Subramanian Sophia Yang Szymon Antoniak Teven Le Scao Th\u00e9ophile Gervet Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2024. Mixtral of Experts. arXiv:2401.04088 [cs.LG] https:\/\/arxiv.org\/abs\/2401.04088"},{"key":"e_1_3_2_1_15_1","first-page":"74","article-title":"Lancet: Accelerating Mixture-of-Experts Training by Overlapping Weight Gradient Computation and All-to-All Communication","volume":"6","author":"Jiang Chenyu","year":"2024","unstructured":"Chenyu Jiang, Ye Tian, Zhen Jia, Chuan Wu, Yida Wang, and Shuai Zheng. 2024. Lancet: Accelerating Mixture-of-Experts Training by Overlapping Weight Gradient Computation and All-to-All Communication. Proceedings of Machine Learning and Systems 6 (2024), 74\u201386.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.33945"},{"key":"e_1_3_2_1_17_1","unstructured":"Jeff Johnson. 2024. DIET-GPU: Efficient Model Inference on GPUs. https:\/\/github.com\/facebookresearch\/dietgpu."},{"key":"e_1_3_2_1_18_1","unstructured":"Dhiraj Kalamkar Dheevatsa Mudigere Naveen Mellempudi Dipankar Das Kunal Banerjee Sasikanth Avancha Dharma Teja Vooturi Nataraj Jammalamadaka Jianyu Huang Hector Yuen Jiyan Yang Jongsoo Park Alexander Heinecke Evangelos Georganas Sudarshan Srinivasan Abhisek Kundu Misha Smelyanskiy Bharat Kaul and Pradeep Dubey. 2019. A Study of BFLOAT16 for Deep Learning Training. arXiv:1905.12322 [cs.LG] https:\/\/arxiv.org\/abs\/1905.12322"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001172"},{"key":"e_1_3_2_1_20_1","unstructured":"Sehoon Kim Coleman Hooper Amir Gholami Zhen Dong Xiuyu Li Sheng Shen Michael W. Mahoney and Kurt Keutzer. 2024. SqueezeLLM: Dense-and-Sparse Quantization. In ICML. OpenReview.net."},{"key":"e_1_3_2_1_21_1","unstructured":"G\u00fcnter Klambauer Thomas Unterthiner Andreas Mayr and Sepp Hochreiter. 2017. Self-Normalizing Neural Networks. In NIPS. 971\u2013980."},{"key":"e_1_3_2_1_22_1","article-title":"Deep Neural Networks with Dependent Weights: Gaussian Process Mixture Limit, Heavy Tails, Sparsity and Compressibility","volume":"24","author":"Lee Hoil","year":"2023","unstructured":"Hoil Lee, Fadhel Ayed, Paul Jung, Juho Lee, Hongseok Yang, and Francois Caron. 2023. Deep Neural Networks with Dependent Weights: Gaussian Process Mixture Limit, Heavy Tails, Sparsity and Compressibility. J. Mach. Learn. Res. 24 (2023), 289:1\u2013289:78.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_23_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Liang Wanchao","year":"2025","unstructured":"Wanchao Liang, Tianyu Liu, Less Wright, Will Constable, Andrew Gu, Chien-Chin Huang, Iris Zhang, Wei Feng, Howard Huang, Junjie Wang, Sanket Purandare, Gokul Nadathur, and Stratos Idreos. 2025. TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","volume-title":"Stochastic Gradient Descent for Gaussian Processes Done Right. In The Twelfth International Conference on Learning Representations.","author":"Lin Jihao Andreas","year":"2024","unstructured":"Jihao Andreas Lin, Shreyas Padhy, Javier Antoran, Austin Tripp, Alexander Terenin, Csaba Szepesvari, Jos\u00e9 Miguel Hern\u00e1ndez-Lobato, and David Janz. 2024. Stochastic Gradient Descent for Gaussian Processes Done Right. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_25_1","volume-title":"Mast: Efficient Training of Mixture-of-Experts Transformers with Task Pipelining and Ordering. In 2025 IEEE 45th International Conference on Distributed Computing Systems. IEEE.","author":"Lin Wenxiang","year":"2025","unstructured":"Wenxiang Lin, Xinglin Pan, Shaohuai Shi, Xuan Wang, Bo Li, and Xiaowen Chu. 2025. Mast: Efficient Training of Mixture-of-Experts Transformers with Task Pipelining and Ordering. In 2025 IEEE 45th International Conference on Distributed Computing Systems. IEEE."},{"key":"e_1_3_2_1_26_1","volume-title":"HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap. arXiv preprint arXiv:2508.09591","author":"Lin Wenxiang","year":"2025","unstructured":"Wenxiang Lin, Xinglin Pan, Lin Zhang, Shaohuai Shi, Xuan Wang, and Xiaowen Chu. 2025. HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap. arXiv preprint arXiv:2508.09591 (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"Zhiying Xu, Zhuang Wang, Ziming Mao, Delong Meng, Jia Zhen, Jun Wu, Ion Stoica, Yida Wang, and Yang Zhou.","author":"Ma Shuang","year":"2026","unstructured":"Shuang Ma, Chon Lam Lao, Zhiying Xu, Zhuang Wang, Ziming Mao, Delong Meng, Jia Zhen, Jun Wu, Ion Stoica, Yida Wang, and Yang Zhou. 2026. UCCL-Zip: Lossless Compression Supercharged GPU Communication. arXiv e-prints (April 2026)."},{"key":"e_1_3_2_1_28_1","unstructured":"Paulius Micikevicius Sharan Narang Jonah Alben Gregory F. Diamos Erich Elsen David Garc\u00eda Boris Ginsburg Michael Houston Oleksii Kuchaiev Ganesh Venkatesh and Hao Wu. 2018. Mixed Precision Training. In ICLR (Poster). Open-Review.net."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_30_1","unstructured":"NVIDIA. 2025. nvcomp: Repository for nvCOMP docs and examples. https:\/\/github.com\/NVIDIA\/nvcomp. Accessed: 2025-08-18."},{"key":"e_1_3_2_1_31_1","unstructured":"NVIDIA. 2026. NCCL (pronounced \"Nickel\") is a stand-alone library of standard communication routines for GPUs. https:\/\/github.com\/NVIDIA\/nccl"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","volume":"1","author":"Pan Xinglin","year":"2025","unstructured":"Xinglin Pan, Wenxiang Lin, Lin Zhang, Shaohuai Shi, Zhenheng Tang, Rui Wang, Bo Li, and Xiaowen Chu. 2025. FSMoE: A flexible and scalable training system for sparse mixture-of-experts models. In Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1. 524\u2013539."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540724"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370870"},{"key":"e_1_3_2_1_35_1","unstructured":"Joshua Peterson Stephan Meylan and David Bourgin. 2019. Open clone of openai's unreleased webtext dataset scraper."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24685-5_1"},{"key":"e_1_3_2_1_37_1","volume-title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations.","author":"Shazeer Noam","year":"2016","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2016. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_38_1","volume-title":"Ka Chun Cheung, and Simon See","author":"Shi Shaohuai","year":"2019","unstructured":"Shaohuai Shi, Xiaowen Chu, Ka Chun Cheung, and Simon See. 2019. Understanding top-k sparsification in distributed deep learning. arXiv preprint arXiv:1911.08772 (2019)."},{"key":"e_1_3_2_1_39_1","volume-title":"IEEE INFOCOM 2023-IEEE Conference on Computer Communications.","author":"Shi Shaohuai","year":"2023","unstructured":"Shaohuai Shi, Xinglin Pan, Xiaowen Chu, and Bo Li. 2023. PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining. In IEEE INFOCOM 2023-IEEE Conference on Computer Communications."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the Nineteenth European Conference on Computer Systems. 236\u2013249","author":"Shi Shaohuai","year":"2024","unstructured":"Shaohuai Shi, Xinglin Pan, Qiang Wang, Chengjian Liu, Xiaozhe Ren, Zhongzhe Hu, Yu Yang, Bo Li, and Xiaowen Chu. 2024. ScheMoE: An Extensible Mixture-of-Experts Distributed Training System with Tasks Scheduling. In Proceedings of the Nineteenth European Conference on Computer Systems. 236\u2013249."},{"key":"e_1_3_2_1_41_1","volume-title":"Unveiling the mystery of weight in large foundation models: Gaussian distribution never fades. arXiv preprint arXiv:2501.10661","author":"Si Chongjie","year":"2025","unstructured":"Chongjie Si, Jingjing Jiang, and Wei Shen. 2025. Unveiling the mystery of weight in large foundation models: Gaussian distribution never fades. arXiv preprint arXiv:2501.10661 (2025)."},{"key":"e_1_3_2_1_42_1","unstructured":"Qwen Team. 2025. Qwen3 Technical Report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"e_1_3_2_1_44_1","volume-title":"Lossless Compression for LLM Tensor Incremental Snapshots. arXiv preprint arXiv:2505.09810","author":"Waddington Daniel","year":"2025","unstructured":"Daniel Waddington and Cornel Constantinescu. 2025. Lossless Compression for LLM Tensor Incremental Snapshots. arXiv preprint arXiv:2505.09810 (2025)."},{"key":"e_1_3_2_1_45_1","volume-title":"Blink: Fast and Generic Collectives for Distributed ML. In MLSys. mlsys.org.","author":"Wang Guanhua","year":"2020","unstructured":"Guanhua Wang, Shivaram Venkataraman, Amar Phanishayee, Jorgen Thelin, Nikhil R. Devanur, and Ion Stoica. 2020. Blink: Fast and Generic Collectives for Distributed ML. In MLSys. mlsys.org."},{"key":"e_1_3_2_1_46_1","volume-title":"SP-MoE: Expediting Mixture-of-Experts Training with Optimized Pipelining Planning. In IEEE INFOCOM 2025-IEEE Conference on Computer Communications.","author":"Wang Ne","year":"2025","unstructured":"Ne Wang, Wenxiang Lin, Lin Zhang, Shaohuai Shi, Ruiting Zhou, and Bo Li. 2025. SP-MoE: Expediting Mixture-of-Experts Training with Optimized Pipelining Planning. In IEEE INFOCOM 2025-IEEE Conference on Computer Communications."},{"key":"e_1_3_2_1_47_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Xi Haocheng","year":"2025","unstructured":"Haocheng Xi, Han Cai, Ligeng Zhu, Yao Lu, Kurt Keutzer, Jianfei Chen, and Song Han. 2025. COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_48_1","volume-title":"Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float. arXiv preprint arXiv:2504.11651","author":"Zhang Tianyi","year":"2025","unstructured":"Tianyi Zhang, Yang Sui, Shaochen Zhong, Vipin Chaudhary, Xia Hu, and Anshumali Shrivastava. 2025. 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float. arXiv preprint arXiv:2504.11651 (2025)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2808233"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Yanli Zhao Andrew Gu Rohan Varma Liang Luo Chien-Chin Huang Min Xu Less Wright Hamid Shojanazeri Myle Ott Sam Shleifer Alban Desmaison Can Balioglu Pritam Damania Bernard Nguyen Geeta Chauhan Yuchen Hao Ajit Mathews and Shen Li. 2023. PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel. arXiv:2304.11277 [cs.DC] https:\/\/arxiv.org\/abs\/2304.11277","DOI":"10.14778\/3611540.3611569"}],"event":{"name":"SIGCOMM '26: ACM SIGCOMM 2026 Conference","location":"Colorado Convention Center Denver CO USA","acronym":"SIGCOMM '26","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2026 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3789240.3829204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:46:19Z","timestamp":1786473979000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3829204"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":50,"alternative-id":["10.1145\/3789240.3829204","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3829204","relation":{},"subject":[],"published":{"date-parts":[[2026,8,11]]},"assertion":[{"value":"2026-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}