{"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":1786476493481,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":46,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3829201","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"550-563","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Balancing and Beyond: Communication-Centric Optimizations in Expert Parallelism"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5468-7366","authenticated-orcid":false,"given":"Jiamin","family":"Cao","sequence":"first","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0007-3828","authenticated-orcid":false,"given":"Qingxu","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4086-9490","authenticated-orcid":false,"given":"Yaozhong","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3548-2030","authenticated-orcid":false,"given":"Jiaqi","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0982-008X","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5661-6617","authenticated-orcid":false,"given":"Shangfeng","family":"Shi","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9057-818X","authenticated-orcid":false,"given":"Zian","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6285-4697","authenticated-orcid":false,"given":"Yizhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8826-4999","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3959-5086","authenticated-orcid":false,"given":"Kunling","family":"He","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4352-7497","authenticated-orcid":false,"given":"Ennan","family":"Zhai","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0939-8943","authenticated-orcid":false,"given":"Jianbo","family":"Dong","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1213-0554","authenticated-orcid":false,"given":"Binzhang","family":"Fu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7272-8143","authenticated-orcid":false,"given":"Dennis","family":"Cai","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2022. ibgda. https:\/\/docs.nvidia.com\/nvshmem\/api\/using.html."},{"key":"e_1_3_2_1_2_1","unstructured":"2022. NVIDIA Hopper Architecture In-Depth. https:\/\/developer.nvidia.com\/blog\/nvidia-hopper-architecture-in-depth\/."},{"key":"e_1_3_2_1_3_1","unstructured":"2024. DeepSpeed. https:\/\/github.com\/microsoft\/DeepSpeed."},{"key":"e_1_3_2_1_4_1","unstructured":"2024. Gloo. https:\/\/github.com\/facebookincubator\/gloo."},{"key":"e_1_3_2_1_5_1","unstructured":"2024. MSCCL-EXECUTOR-NCCL. https:\/\/github.com\/Azure\/msccl-executor-nccl."},{"key":"e_1_3_2_1_6_1","unstructured":"2024. NCCL. https:\/\/github.com\/NVIDIA\/nccl."},{"key":"e_1_3_2_1_7_1","unstructured":"2025. DeepEP. https:\/\/github.com\/deepseek-ai\/DeepEP."},{"key":"e_1_3_2_1_8_1","unstructured":"2025. Expert Parallelism Load Balancer (EPLB). https:\/\/github.com\/deepseek-ai\/EPLB."},{"key":"e_1_3_2_1_9_1","unstructured":"2025. pplx-kernels. https:\/\/github.com\/perplexityai\/pplx-kernels."},{"key":"e_1_3_2_1_10_1","unstructured":"2026. Dual batch overlap. https:\/\/docs.vllm.ai\/en\/latest\/design\/dbo\/."},{"key":"e_1_3_2_1_11_1","unstructured":"2026. rccl. https:\/\/github.com\/ROCm\/rccl."},{"key":"e_1_3_2_1_12_1","unstructured":"2026. SGLang. https:\/\/github.com\/sgl-project\/sglang."},{"key":"e_1_3_2_1_13_1","unstructured":"2026. vllm. https:\/\/github.com\/vllm-project\/vllm."},{"key":"e_1_3_2_1_14_1","unstructured":"Amey Agrawal Nitin Kedia Ashish Panwar Jayashree Mohan Nipun Kwatra Bhargav S. Gulavani Alexey Tumanov and Ramachandran Ramjee. 2024. Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve. In USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/agrawal"},{"key":"e_1_3_2_1_15_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). https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750499"},{"key":"e_1_3_2_1_17_1","unstructured":"Shuo Chen et al. 2024. Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation. arXiv preprint arXiv:2405.01814 (2024). https:\/\/arxiv.org\/abs\/2405.01814"},{"key":"e_1_3_2_1_18_1","first-page":"23049","volume-title":"Oh (Eds.)","volume":"35","author":"Chen Zixiang","year":"2022","unstructured":"Zixiang Chen, Yihe Deng, Yue Wu, Quanquan Gu, and Yuanzhi Li. 2022. Towards Understanding the Mixture-of-Experts Layer in Deep Learning. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 23049-23062. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/91edff07232fb1b55a505a9e9f6c0ff3-Paper-Conference.pdf"},{"key":"e_1_3_2_1_19_1","volume-title":"Optimizing Dynamic Neural Networks with Brainstorm. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Cui Weihao","year":"2023","unstructured":"Weihao Cui, Zhenhua Han, Lingji Ouyang, Yichuan Wang, Ningxin Zheng, Lingxiao Ma, Yuqing Yang, Fan Yang, Jilong Xue, Lili Qiu, Lidong Zhou, Quan Chen, Haisheng Tan, and Minyi Guo. 2023. Optimizing Dynamic Neural Networks with Brainstorm. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). USENIX Association."},{"key":"e_1_3_2_1_20_1","unstructured":"DeepSeek-AI Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi Xiaokang Zhang Xingkai Yu Yu Wu Z. F. Wu Zhibin Gou Zhihong Shao Zhuoshu Li Ziyi Gao Aixin Liu Bing Xue Bingxuan Wang Bochao Wu Bei Feng Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai 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 Honghui Ding Huajian Xin Huazuo Gao Hui Qu Hui Li Jianzhong Guo Jiashi Li Jiawei Wang Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li J. L. Cai Jiaqi Ni Jian Liang Jin Chen Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Liang Zhao Litong Wang Liyue Zhang Lei Xu Leyi Xia Mingchuan Zhang Minghua Zhang Minghui Tang Meng Li Miaojun Wang Mingming Li Ning Tian Panpan Huang Peng Zhang Qiancheng Wang Qinyu Chen Qiushi Du Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang R. J. Chen R. L. Jin Ruyi Chen Shanghao Lu Shangyan Zhou Shanhuang Chen Shengfeng Ye Shiyu Wang Shuiping Yu Shunfeng Zhou Shuting Pan S. S. Li Shuang Zhou Shaoqing Wu Shengfeng Ye Tao Yun Tian Pei Tianyu Sun T. Wang Wangding Zeng Wanjia Zhao Wen Liu Wenfeng Liang Wenjun Gao Wenqin Yu Wentao Zhang W. L. Xiao Wei An Xiaodong Liu Xiaohan Wang Xiaokang Chen Xiaotao Nie Xin Cheng Xin Liu Xin Xie Xingchao Liu Xinyu Yang Xinyuan Li Xuecheng Su Xuheng Lin X. Q. Li Xiangyue Jin Xiaojin Shen Xiaosha Chen Xiaowen Sun Xiaoxiang Wang Xinnan Song Xinyi Zhou Xianzu Wang Xinxia Shan Y. K. Li Y. Q. Wang Y. X. Wei Yang Zhang Yanhong Xu Yao Li Yao Zhao Yaofeng Sun Yaohui Wang Yi Yu Yichao Zhang Yifan Shi Yiliang Xiong Ying He Yishi Piao Yisong Wang Yixuan Tan Yiyang Ma Yiyuan Liu Yongqiang Guo Yuan Ou Yuduan Wang Yue Gong Yuheng Zou Yujia He Yunfan Xiong Yuxiang Luo Yuxiang You Yuxuan Liu Yuyang Zhou Y. X. Zhu Yanhong Xu Yanping Huang Yaohui Li Yi Zheng Yuchen Zhu Yunxian Ma Ying Tang Yukun Zha Yuting Yan Z. Z. Ren Zehui Ren Zhangli Sha Zhe Fu Zhean Xu Zhenda Xie Zhengyan Zhang Zhewen Hao Zhicheng Ma Zhigang Yan Zhiyu Wu Zihui Gu Zijia Zhu Zijun Liu Zilin Li Ziwei Xie Ziyang Song Zizheng Pan Zhen Huang Zhipeng Xu Zhongyu Zhang and Zhen Zhang. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 [cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_1_21_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 Zizheng Pan. 2025. DeepSeek-V3 Technical Report. arXiv:2412.19437 [cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_2_1_22_1","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research 23, 120 (2022), 1\u201339.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_23_1","unstructured":"Yichao Fu et al. 2024. ServerlessLLM: Low-Latency Serverless Inference for Large Language Models. arXiv preprint arXiv:2401.14351 (2024). https:\/\/arxiv.org\/abs\/2401.14351"},{"key":"e_1_3_2_1_24_1","first-page":"288","article-title":"Megablocks: Efficient sparse training with mixture-of-experts","volume":"5","author":"Gale Trevor","year":"2023","unstructured":"Trevor Gale, Deepak Narayanan, Cliff Young, and Matei Zaharia. 2023. Megablocks: Efficient sparse training with mixture-of-experts. Proceedings of Machine Learning and Systems 5 (2023), 288\u2013304.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines. arXiv preprint arXiv:2403.11421","author":"He Jiaao","year":"2024","unstructured":"Jiaao He and Jidong Zhai. 2024. FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines. arXiv preprint arXiv:2403.11421 (2024). https:\/\/arxiv.org\/abs\/2403.11421"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508418"},{"key":"e_1_3_2_1_27_1","first-page":"269","article-title":"Tutel: Adaptive mixture-of-experts at scale","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, et al. 2023. Tutel: Adaptive mixture-of-experts at scale. Proceedings of Machine Learning and Systems 5 (2023), 269\u2013287.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1162\/NECO.1991.3.1.79"},{"key":"e_1_3_2_1_29_1","volume-title":"Joseph E. Gonzalez, Hao Zhang, and Ion Stoica.","author":"Kwon Woosuk","year":"2023","unstructured":"Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient Memory Management for Large Language Model Serving with PagedAttention. arXiv preprint arXiv:2309.06180 (2023). https:\/\/arxiv.org\/abs\/2309.06180"},{"key":"e_1_3_2_1_30_1","volume-title":"Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Max Krikun, Noam Shazeer, and Zhifeng Chen.","author":"Lepikhin Dmitry","year":"2020","unstructured":"Dmitry Lepikhin, Hyouk Joong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Max 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_31_1","volume-title":"Accelerating Distributed MoE Training and Inference with Lina. In 2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Li Jiamin","year":"2023","unstructured":"Jiamin Li, Yimin Jiang, Yibo Zhu, Cong Wang, and Hong Xu. 2023. Accelerating Distributed MoE Training and Inference with Lina. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). USENIX Association."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604869"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672249"},{"key":"e_1_3_2_1_34_1","volume-title":"AMoE: Adaptive Mixture-of-Experts for Efficient Load Balancing in Serving. arXiv preprint arXiv:2505.08944","author":"Nie Xiaonan","year":"2025","unstructured":"Xiaonan Nie, Pinxue Zhao, Xupeng Miao, Jiangfei Duan, and Bin Cui. 2025. AMoE: Adaptive Mixture-of-Experts for Efficient Load Balancing in Serving. arXiv preprint arXiv:2505.08944 (2025)."},{"key":"e_1_3_2_1_35_1","unstructured":"Alibaba Cloud Qwen Team. 2025. Qwen3-Coder. https:\/\/github.com\/QwenLM\/Qwen3-Coder"},{"key":"e_1_3_2_1_36_1","volume-title":"International conference on machine learning. PMLR","author":"Rajbhandari Samyam","year":"2022","unstructured":"Samyam Rajbhandari, Conglong Li, Zhewei Yao, Minjia Zhang, Reza Yazdani Aminabadi, Ammar Ahmad 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. PMLR, 18332\u201318346."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527382"},{"key":"e_1_3_2_1_38_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 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\u201319, 2023, Mahesh Balakrishnan and Manya Ghobadi (Eds.). USENIX Association, 593\u2013612. https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/shah"},{"key":"e_1_3_2_1_39_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc V. Le, Geoffrey E. Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"e_1_3_2_1_40_1","volume-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Piotr Maziarz, Andy Davis, Quoc V Le, Geoffrey Hinton, and Jeffrey Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)."},{"key":"e_1_3_2_1_41_1","volume-title":"Llumnix: Dynamic Scheduling for Large Language Model Serving. arXiv preprint arXiv:2406.03243","author":"Biao Sun","year":"2024","unstructured":"Biao Sun et al. 2024. Llumnix: Dynamic Scheduling for Large Language Model Serving. arXiv preprint arXiv:2406.03243 (2024). https:\/\/arxiv.org\/abs\/2406.03243"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the Third Conference on Machine Learning and Systems, MLSys 2020","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 Proceedings of the Third Conference on Machine Learning and Systems, MLSys 2020, Austin, TX, USA, March 2\u20134, 2020, Inderjit S. Dhillon, Dimitris S. Papailiopoulos, and Vivienne Sze (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2020\/hash\/cd3a9a55f7f3723133fa4a13628cdf03-Abstract.html"},{"key":"e_1_3_2_1_43_1","volume-title":"USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/wu-bingyang","author":"Bingyang","unstructured":"Bingyang Wu et al. 2024. dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving. In USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/wu-bingyang"},{"key":"e_1_3_2_1_44_1","volume-title":"Byeonghyeon Lee, Jaehoon Sohn, Yongsub Oh, et al.","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Younggyu Jeong, Geon-Woo Kim, Soojeong Lee, Hyeonwoo Kim, Joo Seong Lee, Byeonghyeon Lee, Jaehoon Sohn, Yongsub Oh, et al. 2022. Orca: A Distributed Serving System for Transformer-Based Generative Models. In USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu"},{"key":"e_1_3_2_1_45_1","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Zhang Zhihao","year":"2023","unstructured":"Zhihao Zhang and Yibo Zhu. 2023. SmartMoE: Efficiently Training Sparsely-Activated Models through Combining Offline and Online Parallelism. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). USENIX Association."},{"key":"e_1_3_2_1_46_1","volume-title":"MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism. arXiv preprint arXiv:2504.02263","author":"Zhu Ruidong","year":"2025","unstructured":"Ruidong Zhu, Ziheng Jiang, Chao Jin, Peng Wu, Cesar A. Stuardo, Dongyang Wang, Xinlei Zhang, Huaping Zhou, Haoran Wei, Yang Cheng, Jianzhe Xiao, Xinyi Zhang, Lingjun Liu, Haibin Lin, Li-Wen Chang, Jianxi Ye, Xiao Yu, Xuanzhe Liu, Xin Jin, and Xin Liu. 2025. MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism. arXiv preprint arXiv:2504.02263 (2025). https:\/\/arxiv.org\/abs\/2504.02263"}],"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\/3789240.3829201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:46:28Z","timestamp":1786473988000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3829201"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":46,"alternative-id":["10.1145\/3789240.3829201","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3829201","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"}}]}}