{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T05:12:09Z","timestamp":1783746729143,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":50,"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-nc-nd\/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\/3806645.3807818","type":"proceedings-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:21:11Z","timestamp":1783743671000},"page":"387-401","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["UniEP: Unified Expert-Parallel MegaKernel MoE for LLM Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9471-1780","authenticated-orcid":false,"given":"Size","family":"Zheng","sequence":"first","affiliation":[{"name":"ByteDance Seed, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4635-7309","authenticated-orcid":false,"given":"Xuegui","family":"Zheng","sequence":"additional","affiliation":[{"name":"Bytedance Seed, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6515-6733","authenticated-orcid":false,"given":"Li-Wen","family":"Chang","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Beijing, 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, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities. CoRR abs\/2308.12966 (2023). arXiv:https:\/\/arXiv.org\/abs\/2308.1296610.48550\/ARXIV.2308.12966","DOI":"10.48550\/ARXIV.2308.12966"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Yifan Bai Yiping Bao Guanduo Chen Jiahao Chen Ningxin Chen Ruijue Chen Yanru Chen Yuankun Chen Yutian Chen Zhuofu Chen Jialei Cui Hao Ding Mengnan Dong Angang Du Chenzhuang Du Dikang Du Yulun Du Yu Fan Yichen Feng Kelin Fu Bofei Gao Hongcheng Gao Peizhong Gao Tong Gao Xinran Gu Longyu Guan Haiqing Guo Jianhang Guo Hao Hu Xiaoru Hao Tianhong He Weiran He Wenyang He Chao Hong Yangyang Hu Zhenxing Hu Weixiao Huang Zhiqi Huang Zihao Huang Tao Jiang Zhejun Jiang Xinyi Jin Yongsheng Kang Guokun Lai Cheng Li Fang Li Haoyang Li Ming Li Wentao Li Yanhao Li Yiwei Li Zhaowei Li Zheming Li Hongzhan Lin Xiaohan Lin Zongyu Lin Chengyin Liu Chenyu Liu Hongzhang Liu Jingyuan Liu Junqi Liu Liang Liu Shaowei Liu T.\u00a0Y. Liu Tianwei Liu Weizhou Liu Yangyang Liu Yibo Liu Yiping Liu Yue Liu Zhengying Liu Enzhe Lu Lijun Lu Shengling Ma Xinyu Ma Yingwei Ma Shaoguang Mao Jie Mei Xin Men Yibo Miao Siyuan Pan Yebo Peng Ruoyu Qin Bowen Qu Zeyu Shang Lidong Shi Shengyuan Shi Feifan Song Jianlin Su Zhengyuan Su Xinjie Sun Flood Sung Heyi Tang Jiawen Tao Qifeng Teng Chensi Wang Dinglu Wang Feng Wang and Haiming Wang. 2025. Kimi K2: Open Agentic Intelligence. CoRR abs\/2507.20534 (2025). arXiv:https:\/\/arXiv.org\/abs\/2507.2053410.48550\/ARXIV.2507.20534","DOI":"10.48550\/ARXIV.2507.20534"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441620"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Li-Wen Chang Wenlei Bao Qi Hou Chengquan Jiang Ningxin Zheng Yinmin Zhong Xuanrun Zhang Zuquan Song Ziheng Jiang Haibin Lin Xin Jin and Xin Liu. 2024. FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion. CoRR abs\/2406.06858 (2024). arXiv:https:\/\/arXiv.org\/abs\/2406.0685810.48550\/ARXIV.2406.06858","DOI":"10.48550\/ARXIV.2406.06858"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651379"},{"key":"e_1_3_3_1_7_2","first-page":"578","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018, Carlsbad, CA, USA, October 8-10, 2018","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie\u00a0Q. Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018, Carlsbad, CA, USA, October 8-10, 2018, Andrea\u00a0C. Arpaci-Dusseau and Geoff Voelker (Eds.). USENIX Association, 578\u2013594."},{"key":"e_1_3_3_1_8_2","unstructured":"Meghan Cowan Saeed Maleki Madanlal Musuvathi Olli Saarikivi and Yifan Xiong. 2022. GC3: An Optimizing Compiler for GPU Collective Communication. arxiv:https:\/\/arXiv.org\/abs\/2201.11840\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2201.11840"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Tri Dao Daniel\u00a0Y. Fu Stefano Ermon Atri Rudra and Christopher R\u00e9. 2022. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. CoRR abs\/2205.14135 (2022). arXiv:https:\/\/arXiv.org\/abs\/2205.1413510.48550\/arXiv.2205.14135","DOI":"10.48550\/arXiv.2205.14135"},{"key":"e_1_3_3_1_10_2","unstructured":"Google DeepMind. 2025. Gemini 3 Pro: Best for complex tasks and bringing creative concepts to life. https:\/\/deepmind.google\/models\/gemini\/pro\/"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. CoRR abs\/2501.12948 (2025). arXiv:https:\/\/arXiv.org\/abs\/2501.1294810.48550\/ARXIV.2501.12948","DOI":"10.48550\/ARXIV.2501.12948"},{"key":"e_1_3_3_1_12_2","unstructured":"DeepSeek-AI. 2025. EPLB: Expert Parallelism Load Balancer. https:\/\/github.com\/deepseek-ai\/EPLB. GitHub repository."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bin Wang Bingxuan Wang Bo Liu Chenggang Zhao Chengqi Deng Chong Ruan Damai Dai Daya Guo Dejian Yang Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fuli Luo Guangbo Hao Guanting Chen Guowei Li Hao Zhang Hanwei Xu Hao Yang Haowei Zhang Honghui Ding Huajian Xin Huazuo Gao Hui Li Hui Qu J.\u00a0L. Cai Jian Liang Jianzhong Guo Jiaqi Ni Jiashi Li Jin Chen Jingyang Yuan Junjie Qiu Junxiao Song Kai Dong Kaige Gao Kang Guan Lean Wang Lecong Zhang Lei Xu Leyi Xia Liang Zhao Liyue Zhang Meng Li Miaojun Wang Mingchuan Zhang Minghua Zhang Minghui Tang Mingming Li Ning Tian Panpan Huang Peiyi Wang Peng Zhang Qihao Zhu Qinyu Chen Qiushi Du R.\u00a0J. Chen R.\u00a0L. Jin Ruiqi Ge Ruizhe Pan Runxin Xu Ruyi Chen S.\u00a0S. Li Shanghao Lu Shangyan Zhou Shanhuang Chen Shaoqing Wu Shengfeng Ye Shirong Ma Shiyu Wang Shuang Zhou Shuiping Yu Shunfeng Zhou Size Zheng Tao Wang Tian Pei Tian Yuan Tianyu Sun W.\u00a0L. Xiao Wangding Zeng Wei An Wen Liu Wenfeng Liang Wenjun Gao Wentao Zhang X.\u00a0Q. Li Xiangyue Jin Xianzu Wang Xiao Bi Xiaodong Liu Xiaohan Wang Xiaojin Shen Xiaokang Chen Xiaosha Chen Xiaotao Nie and Xiaowen Sun. 2024. DeepSeek-V2: A Strong Economical and Efficient Mixture-of-Experts Language Model. CoRR abs\/2405.04434 (2024). arXiv:https:\/\/arXiv.org\/abs\/2405.0443410.48550\/ARXIV.2405.04434","DOI":"10.48550\/ARXIV.2405.04434"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","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.\u00a0L. 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.\u00a0J. Chen R.\u00a0L. Jin Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang Runxin Xu Ruoyu Zhang Ruyi Chen S.\u00a0S. 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.\u00a0L. Xiao and Wangding Zeng. 2024. DeepSeek-V3 Technical Report. CoRR abs\/2412.19437 (2024). arXiv:https:\/\/arXiv.org\/abs\/2412.1943710.48550\/ARXIV.2412.19437","DOI":"10.48550\/ARXIV.2412.19437"},{"key":"e_1_3_3_1_15_2","volume-title":"Proceedings of the Sixth Conference on Machine Learning and Systems, MLSys 2023, Miami, FL, USA, June 4-8, 2023","author":"Gale Trevor","year":"2023","unstructured":"Trevor Gale, Deepak Narayanan, Cliff Young, and Matei Zaharia. 2023. MegaBlocks: Efficient Sparse Training with Mixture-of-Experts. In Proceedings of the Sixth Conference on Machine Learning and Systems, MLSys 2023, Miami, FL, USA, June 4-8, 2023, Dawn Song, Michael Carbin, and Tianqi Chen (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/hash\/5a54f79333768effe7e8927bcccffe40-Abstract-mlsys2023.html"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508418"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507778"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Chao Jin Ziheng Jiang Zhihao Bai Zheng Zhong Juncai Liu Xiang Li Ningxin Zheng Xi Wang Cong Xie Qi Huang Wen Heng Yiyuan Ma Wenlei Bao Size Zheng Yanghua Peng Haibin Lin Xuanzhe Liu Xin Jin and Xin Liu. 2025. MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production. CoRR abs\/2505.11432 (2025). arXiv:https:\/\/arXiv.org\/abs\/2505.1143210.48550\/ARXIV.2505.11432","DOI":"10.48550\/ARXIV.2505.11432"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_3_1_20_2","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. 2024. TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training. arxiv:https:\/\/arXiv.org\/abs\/2410.06511\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2410.06511"},{"key":"e_1_3_3_1_21_2","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025","author":"Liu Xinyi","year":"2025","unstructured":"Xinyi Liu, Yujie Wang, Fangcheng Fu, Xupeng Miao, Shenhan Zhu, Xiaonan Nie, and Bin Cui. 2025. NetMoE: Accelerating MoE Training through Dynamic Sample Placement. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=1qP3lsatCR"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","unstructured":"Haoyu Lu Wen Liu Bo Zhang Bingxuan Wang Kai Dong Bo Liu Jingxiang Sun Tongzheng Ren Zhuoshu Li Hao Yang Yaofeng Sun Chengqi Deng Hanwei Xu Zhenda Xie and Chong Ruan. 2024. DeepSeek-VL: Towards Real-World Vision-Language Understanding. CoRR abs\/2403.05525 (2024). arXiv:https:\/\/arXiv.org\/abs\/2403.0552510.48550\/ARXIV.2403.05525","DOI":"10.48550\/ARXIV.2403.05525"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_3_1_24_2","volume-title":"cuBLAS","year":"2022","unstructured":"NVIDIA. 2022. cuBLAS. https:\/\/developer.nvidia.com\/cublas"},{"key":"e_1_3_3_1_25_2","volume-title":"CUTLASS","year":"2022","unstructured":"Nvidia. 2022. CUTLASS. https:\/\/github.com\/NVIDIA\/cutlass"},{"key":"e_1_3_3_1_26_2","unstructured":"NVIDIA. 2022. Transformer Engine. https:\/\/github.com\/NVIDIA\/TransformerEngine"},{"key":"e_1_3_3_1_27_2","unstructured":"NVIDIA. 2024. NVIDIA Collective Communications Library. https:\/\/developer.nvidia.com\/nccl."},{"key":"e_1_3_3_1_28_2","volume-title":"NVSHMEM","year":"2025","unstructured":"NVIDIA. 2025. NVSHMEM. https:\/\/docs.nvidia.com\/nvshmem\/api\/using.html"},{"key":"e_1_3_3_1_29_2","volume-title":"CuDNN","year":"2026","unstructured":"Nvidia. 2026. CuDNN. https:\/\/developer.nvidia.com\/cudnn"},{"key":"e_1_3_3_1_30_2","volume-title":"CuTile","year":"2026","unstructured":"Nvidia. 2026. CuTile. https:\/\/github.com\/NVIDIA\/cutile-python"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_3_1_32_2","series-title":"Proceedings of Machine Learning Research","first-page":"18332","volume-title":"International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA","volume":"162","author":"Rajbhandari Samyam","year":"2022","unstructured":"Samyam Rajbhandari, Conglong Li, Zhewei Yao, Minjia Zhang, Reza\u00a0Yazdani Aminabadi, Ammar\u00a0Ahmad Awan, Jeff Rasley, and Yuxiong He. 2022. DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA(Proceedings of Machine Learning Research, Vol.\u00a0162), Kamalika Chaudhuri, Stefanie Jegelka, Le\u00a0Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 18332\u201318346. https:\/\/proceedings.mlr.press\/v162\/rajbhandari22a.html"},{"key":"e_1_3_3_1_33_2","first-page":"593","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023, Boston, MA, April 17-19, 2023","author":"Shah Aashaka","year":"2023","unstructured":"Aashaka Shah, Vijay Chidambaram, Meghan Cowan, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Jacob Nelson, and Olli Saarikivi. 2023. TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches. In 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023, Boston, MA, April 17-19, 2023, Mahesh Balakrishnan and Manya Ghobadi (Eds.). USENIX Association, 593\u2013612. https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/shah"},{"key":"e_1_3_3_1_34_2","unstructured":"Aashaka Shah Abhinav Jangda Binyang Li Caio Rocha Changho Hwang Jithin Jose Madan Musuvathi Olli Saarikivi Peng Cheng Qinghua Zhou Roshan Dathathri Saeed Maleki and Ziyue Yang. 2025. MSCCL++: Rethinking GPU Communication Abstractions for Cutting-edge AI Applications. arxiv:https:\/\/arXiv.org\/abs\/2504.09014\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2504.09014"},{"key":"e_1_3_3_1_35_2","unstructured":"Aaditya Singh Adam Fry Adam Perelman Adam Tart Adi Ganesh Ahmed El-Kishky Aidan McLaughlin Aiden Low AJ Ostrow Akhila Ananthram Akshay Nathan Alan Luo Alec Helyar Aleksander Madry Aleksandr Efremov Aleksandra Spyra Alex Baker-Whitcomb Alex Beutel Alex Karpenko Alex Makelov Alex Neitz Alex Wei Alexandra Barr Alexandre Kirchmeyer Alexey Ivanov Alexi Christakis Alistair Gillespie Allison Tam Ally Bennett Alvin Wan Alyssa Huang Amy\u00a0McDonald Sandjideh Amy Yang Ananya Kumar Andre Saraiva Andrea Vallone Andrei Gheorghe Andres\u00a0Garcia Garcia Andrew Braunstein Andrew Liu Andrew Schmidt Andrey Mereskin Andrey Mishchenko Andy Applebaum Andy Rogerson Ann Rajan Annie Wei Anoop Kotha Anubha Srivastava Anushree Agrawal Arun Vijayvergiya Ashley Tyra Ashvin Nair Avi Nayak Ben Eggers Bessie Ji Beth Hoover Bill Chen Blair Chen Boaz Barak Borys Minaiev Botao Hao Bowen Baker Brad Lightcap Brandon McKinzie Brandon Wang Brendan Quinn Brian Fioca Brian Hsu Brian Yang Brian Yu Brian Zhang Brittany Brenner Callie\u00a0Riggins Zetino Cameron Raymond Camillo Lugaresi Carolina Paz Cary Hudson Cedric Whitney Chak Li Charles Chen Charlotte Cole Chelsea Voss Chen Ding Chen Shen Chengdu Huang Chris Colby Chris Hallacy Chris Koch Chris Lu Christina Kaplan Christina Kim CJ Minott-Henriques Cliff Frey Cody Yu Coley Czarnecki Colin Reid Colin Wei Cory Decareaux Cristina Scheau Cyril Zhang Cyrus Forbes Da Tang Dakota Goldberg Dan Roberts Dana Palmie Daniel Kappler Daniel Levine Daniel Wright Dave Leo David Lin David Robinson Declan Grabb Derek Chen Derek Lim Derek Salama Dibya Bhattacharjee Dimitris Tsipras Dinghua Li Dingli Yu DJ Strouse Drew Williams Dylan Hunn Ed Bayes Edwin Arbus Ekin Akyurek Elaine\u00a0Ya Le Elana Widmann Eli Yani Elizabeth Proehl Enis Sert Enoch Cheung Eri Schwartz Eric Han Eric Jiang Eric Mitchell Eric Sigler Eric Wallace Erik Ritter Erin Kavanaugh Evan Mays Evgenii Nikishin Fangyuan Li Felipe\u00a0Petroski Such Filipe de Avila Belbute\u00a0Peres Filippo Raso Florent Bekerman Foivos Tsimpourlas Fotis Chantzis Francis Song Francis Zhang Gaby Raila Garrett McGrath Gary Briggs Gary Yang Giambattista Parascandolo Gildas Chabot Grace Kim Grace Zhao Gregory Valiant Guillaume Leclerc Hadi Salman Hanson Wang Hao Sheng Haoming Jiang Haoyu Wang Haozhun Jin Harshit Sikchi Heather Schmidt Henry Aspegren Honglin Chen Huida Qiu Hunter Lightman Ian Covert Ian Kivlichan Ian Silber Ian Sohl Ibrahim Hammoud Ignasi Clavera Ikai Lan Ilge Akkaya Ilya Kostrikov Irina Kofman Isak Etinger Ishaan Singal Jackie Hehir Jacob Huh Jacqueline Pan Jake Wilczynski Jakub Pachocki James Lee James Quinn Jamie Kiros Janvi Kalra Jasmyn Samaroo Jason Wang Jason Wolfe Jay Chen Jay Wang Jean Harb Jeffrey Han Jeffrey Wang Jennifer Zhao Jeremy Chen Jerene Yang Jerry Tworek Jesse Chand Jessica Landon Jessica Liang Ji Lin Jiancheng Liu Jianfeng Wang Jie Tang Jihan Yin Joanne Jang Joel Morris Joey Flynn Johannes Ferstad Johannes Heidecke John Fishbein John Hallman Jonah Grant Jonathan Chien Jonathan Gordon Jongsoo Park Jordan Liss Jos Kraaijeveld Joseph Guay Joseph Mo Josh Lawson Josh McGrath Joshua Vendrow Joy Jiao Julian Lee Julie Steele Julie Wang Junhua Mao Kai Chen Kai Hayashi Kai Xiao Kamyar Salahi Kan Wu Karan Sekhri Karan Sharma Karan Singhal Karen Li Kenny Nguyen Keren Gu-Lemberg Kevin King Kevin Liu Kevin Stone Kevin Yu Kristen Ying Kristian Georgiev Kristie Lim Kushal Tirumala Kyle Miller Lama Ahmad Larry Lv Laura Clare Laurance Fauconnet Lauren Itow Lauren Yang Laurentia Romaniuk Leah Anise Lee Byron Leher Pathak Leon Maksin Leyan Lo Leyton Ho Li Jing Liang Wu Liang Xiong Lien Mamitsuka Lin Yang Lindsay McCallum Lindsey Held Liz Bourgeois Logan Engstrom Lorenz Kuhn Louis Feuvrier Lu Zhang Lucas Switzer Lukas Kondraciuk Lukasz Kaiser Manas Joglekar Mandeep Singh Mandip Shah Manuka Stratta Marcus Williams Mark Chen Mark Sun Marselus Cayton Martin Li Marvin Zhang Marwan Aljubeh Matt Nichols Matthew Haines Max Schwarzer Mayank Gupta Meghan Shah Melody Huang Meng Dong Mengqing Wang Mia Glaese Micah Carroll Michael Lampe Michael Malek Michael Sharman Michael Zhang Michele Wang Michelle Pokrass Mihai Florian Mikhail Pavlov Miles Wang Ming Chen Mingxuan Wang Minnia Feng Mo Bavarian Molly Lin Moose Abdool Mostafa Rohaninejad Nacho Soto Natalie Staudacher Natan LaFontaine Nathan Marwell Nelson Liu Nick Preston Nick Turley Nicklas Ansman Nicole Blades Nikil Pancha Nikita Mikhaylin Niko Felix Nikunj Handa Nishant Rai Nitish Keskar Noam Brown Ofir Nachum Oleg Boiko Oleg Murk Olivia Watkins Oona Gleeson Pamela Mishkin Patryk Lesiewicz Paul Baltescu Pavel Belov Peter Zhokhov Philip Pronin Phillip Guo Phoebe Thacker Qi Liu Qiming Yuan Qinghua Liu Rachel Dias Rachel Puckett Rahul Arora Ravi\u00a0Teja Mullapudi Raz Gaon Reah Miyara Rennie Song Rishabh Aggarwal RJ Marsan Robel Yemiru Robert Xiong Rohan Kshirsagar Rohan Nuttall Roman Tsiupa Ronen Eldan Rose Wang Roshan James Roy Ziv Rui Shu Ruslan Nigmatullin Saachi Jain Saam Talaie Sam Altman Sam Arnesen Sam Toizer Sam Toyer Samuel Miserendino Sandhini Agarwal Sarah Yoo Savannah Heon Scott Ethersmith Sean Grove Sean Taylor Sebastien Bubeck Sever Banesiu Shaokyi Amdo Shengjia Zhao Sherwin Wu Shibani Santurkar Shiyu Zhao Shraman\u00a0Ray Chaudhuri Shreyas Krishnaswamy Shuaiqi Xia Shuyang Cheng Shyamal Anadkat Sim\u00f3n\u00a0Posada Fishman Simon Tobin Siyuan Fu Somay Jain Song Mei Sonya Egoian Spencer Kim Spug Golden SQ Mah Steph Lin Stephen Imm Steve Sharpe Steve Yadlowsky Sulman Choudhry Sungwon Eum Suvansh Sanjeev Tabarak Khan Tal Stramer Tao Wang Tao Xin Tarun Gogineni Taya Christianson Ted Sanders Tejal Patwardhan Thomas Degry Thomas Shadwell Tianfu Fu Tianshi Gao Timur Garipov Tina Sriskandarajah Toki Sherbakov Tomer Kaftan Tomo Hiratsuka Tongzhou Wang Tony Song Tony Zhao Troy Peterson Val Kharitonov Victoria Chernova Vineet Kosaraju Vishal Kuo Vitchyr Pong Vivek Verma Vlad Petrov Wanning Jiang Weixing Zhang Wenda Zhou Wenlei Xie Wenting Zhan Wes McCabe Will DePue Will Ellsworth Wulfie Bain Wyatt Thompson Xiangning Chen Xiangyu Qi Xin Xiang Xinwei Shi Yann Dubois Yaodong Yu Yara Khakbaz Yifan Wu Yilei Qian Yin\u00a0Tat Lee Yinbo Chen Yizhen Zhang Yizhong Xiong Yonglong Tian Young Cha Yu Bai Yu Yang Yuan Yuan Yuanzhi Li Yufeng Zhang Yuguang Yang Yujia Jin Yun Jiang Yunyun Wang Yushi Wang Yutian Liu Zach Stubenvoll Zehao Dou Zheng Wu and Zhigang Wang. 2025. OpenAI GPT-5 System Card. arxiv:https:\/\/arXiv.org\/abs\/2601.03267\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2601.03267"},{"key":"e_1_3_3_1_36_2","unstructured":"Benjamin Spector Jordan Juravsky Stuart Sul Owen Dugan Dylan Lim Dan Fu Simran Arora and Chris R\u00e9. 2025. Look ma no bubbles! Designing a low-latency Megakernel for LLAMA-1B. https:\/\/hazyresearch.stanford.edu\/blog\/2025-05-27-no-bubbles. Hazy Research Blog."},{"key":"e_1_3_3_1_37_2","unstructured":"TileLang-Team. 2025. TileLang. https:\/\/github.com\/tile-ai\/tilelang"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_3_1_39_2","unstructured":"Haoran Wei Yaofeng Sun and Yukun Li. 2026. DeepSeek-OCR 2: Visual Causal Flow. arxiv:https:\/\/arXiv.org\/abs\/2601.20552\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2601.20552"},{"key":"e_1_3_3_1_40_2","volume-title":"19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25)","author":"Wu Mengdi","year":"2025","unstructured":"Mengdi Wu, Xinhao Cheng, Shengyu Liu, Chunan Shi, Jianan Ji, Kit Ao, Praveen Velliengiri, Xupeng Miao, Oded Padon, and Zhihao Jia. 2025. Mirage: A Multi-Level Superoptimizer for Tensor Programs. In 19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25). USENIX Association, Boston, MA."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","unstructured":"Yongji Wu Xueshen Liu Shuowei Jin Ceyu Xu Feng Qian Z.\u00a0Morley Mao Matthew Lentz Danyang Zhuo and Ion Stoica. 2025. HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs. CoRR abs\/2504.03871 (2025). arXiv:https:\/\/arXiv.org\/abs\/2504.0387110.48550\/ARXIV.2504.03871","DOI":"10.48550\/ARXIV.2504.03871"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv Chujie Zheng Dayiheng Liu Fan Zhou Fei Huang Feng Hu Hao Ge Haoran Wei Huan Lin Jialong Tang Jian Yang Jianhong Tu Jianwei Zhang Jian Yang Jiaxi Yang Jingren Zhou Jingren Zhou Junyang Lin Kai Dang Keqin Bao Kexin Yang Le Yu Lianghao Deng Mei Li Mingfeng Xue Mingze Li Pei Zhang Peng Wang Qin Zhu Rui Men Ruize Gao Shixuan Liu Shuang Luo Tianhao Li Tianyi Tang Wenbiao Yin Xingzhang Ren Xinyu Wang Xinyu Zhang Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yinger Zhang Yu Wan Yuqiong Liu Zekun Wang Zeyu Cui Zhenru Zhang Zhipeng Zhou and Zihan Qiu. 2025. Qwen3 Technical Report. CoRR abs\/2505.09388 (2025). arXiv:https:\/\/arXiv.org\/abs\/2505.0938810.48550\/ARXIV.2505.09388","DOI":"10.48550\/ARXIV.2505.09388"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","unstructured":"Weihao Yang Hao Huang Donglei Wu Ningke Li Yanqi Pan Qiyang Zheng Wen Xia Shiyi Li and Qiang Wang. 2025. HybridEP: Scaling Expert Parallelism to Cross-Datacenter Scenario via Hybrid Expert\/Data Transmission. CoRR abs\/2510.19470 (2025). arXiv:https:\/\/arXiv.org\/abs\/2510.1947010.48550\/ARXIV.2510.19470","DOI":"10.48550\/ARXIV.2510.19470"},{"key":"e_1_3_3_1_44_2","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.01005 (2025). https:\/\/arxiv.org\/abs\/2501.01005"},{"key":"e_1_3_3_1_45_2","unstructured":"Jiyuan Zhang Yining Liu Siqi Yan Lisen Deng Jennifer Cao Shuqi Yang Min Ni Bi Xue and Shen Li. 2026. MoEBlaze: Breaking the Memory Wall for Efficient MoE Training on Modern GPUs. arxiv:https:\/\/arXiv.org\/abs\/2601.05296\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2601.05296"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","unstructured":"Shulai Zhang Ningxin Zheng Haibin Lin Ziheng Jiang Wenlei Bao Chengquan Jiang Qi Hou Weihao Cui Size Zheng Li-Wen Chang Quan Chen and Xin Liu. 2025. Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts. CoRR abs\/2502.19811 (2025). arXiv:https:\/\/arXiv.org\/abs\/2502.1981110.48550\/ARXIV.2502.19811","DOI":"10.48550\/ARXIV.2502.19811"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","unstructured":"Yu Zhang Zongyu Lin Xingcheng Yao Jiaxi Hu Fanqing Meng Chengyin Liu Xin Men Songlin Yang Zhiyuan Li Wentao Li Enzhe Lu Weizhou Liu Yanru Chen Weixin Xu Longhui Yu Yejie Wang Yu Fan Longguang Zhong Enming Yuan Dehao Zhang Yizhi Zhang T.\u00a0Y. Liu Haiming Wang Shengjun Fang Weiran He Shaowei Liu Yiwei Li Jianlin Su Jiezhong Qiu Bo Pang Junjie Yan Zhejun Jiang Weixiao Huang Bohong Yin Jiacheng You Chu Wei Zhengtao Wang Chao Hong Yutian Chen Guanduo Chen Yucheng Wang Huabin Zheng Feng Wang Yibo Liu Mengnan Dong Zheng Zhang Siyuan Pan Wenhao Wu Yuhao Wu Longyu Guan Jiawen Tao Guohong Fu Xinran Xu Yuzhi Wang Guokun Lai Yuxin Wu Xinyu Zhou Zhilin Yang and Yulun Du. 2025. Kimi Linear: An Expressive Efficient Attention Architecture. CoRR abs\/2510.26692 (2025). arXiv:https:\/\/arXiv.org\/abs\/2510.2669210.48550\/ARXIV.2510.26692","DOI":"10.48550\/ARXIV.2510.26692"},{"key":"e_1_3_3_1_48_2","unstructured":"Chenggang Zhao Shangyan Zhou Liyue Zhang Chengqi Deng Zhean Xu Yuxuan Liu Kuai Yu Jiashi Li and Liang Zhao. 2025. DeepEP: an efficient expert-parallel communication library. https:\/\/github.com\/deepseek-ai\/DeepEP."},{"key":"e_1_3_3_1_49_2","unstructured":"Size Zheng Wenlei Bao Qi Hou Xuegui Zheng Jin Fang Chenhui Huang Tianqi Li Haojie Duanmu Renze Chen Ruifan Xu Yifan Guo Ningxin Zheng Ziheng Jiang Xinyi Di Dongyang Wang Jianxi Ye Haibin Lin Li-Wen Chang Liqiang Lu Yun Liang Jidong Zhai and Xin Liu. 2025. Triton-distributed: Programming Overlapping Kernels on Distributed AI Systems with the Triton Compiler. arxiv:https:\/\/arXiv.org\/abs\/2504.19442\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2504.19442"},{"key":"e_1_3_3_1_50_2","unstructured":"Size Zheng Jin Fang Xuegui Zheng Qi Hou Wenlei Bao Ningxin Zheng Ziheng Jiang Dongyang Wang Jianxi Ye Haibin Lin Li-Wen Chang and Xin Liu. 2025. TileLink: Generating Efficient Compute-Communication Overlapping Kernels using Tile-Centric Primitives. arxiv:https:\/\/arXiv.org\/abs\/2503.20313\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2503.20313"},{"key":"e_1_3_3_1_51_2","unstructured":"Ruidong Zhu Ziheng Jiang Chao Jin Peng Wu Cesar\u00a0A Stuardo Dongyang Wang Xinlei Zhang Huaping Zhou Haoran Wei Yang Cheng et\u00a0al. 2025. Megascale-infer: Serving mixture-of-experts at scale with disaggregated expert parallelism. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.02263 (2025)."}],"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":"2026-07-11T04:21:19Z","timestamp":1783743679000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3806645.3807818"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":50,"alternative-id":["10.1145\/3806645.3807818","10.1145\/3806645"],"URL":"https:\/\/doi.org\/10.1145\/3806645.3807818","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"}}]}}