{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T17:00:58Z","timestamp":1790960458361,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":118,"publisher":"ACM","funder":[{"name":"Hong Kong RGC","award":["TRS T41-603\/20R"],"award-info":[{"award-number":["TRS T41-603\/20R"]}]},{"name":"ITC ACCESS"},{"name":"EmbedWay research projec"},{"name":"Beijing Municipal Science and Technology","award":["Z241100004224023"],"award-info":[{"award-number":["Z241100004224023"]}]},{"name":"NSFC Excellent Young Scientists Fund Program (Overseas)"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3718958.3750465","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:54:11Z","timestamp":1756313651000},"page":"554-574","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["MixNet: A Runtime Reconfigurable Optical-Electrical Fabric for Distributed Mixture-of-Experts Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8380-1879","authenticated-orcid":false,"given":"Xudong","family":"Liao","sequence":"first","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2831-0012","authenticated-orcid":false,"given":"Yijun","family":"Sun","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3238-8500","authenticated-orcid":false,"given":"Han","family":"Tian","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6503-5309","authenticated-orcid":false,"given":"Xinchen","family":"Wan","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-7622","authenticated-orcid":false,"given":"Yilun","family":"Jin","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3184-4081","authenticated-orcid":false,"given":"Zilong","family":"Wang","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8779-4768","authenticated-orcid":false,"given":"Zhenghang","family":"Ren","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4830-7808","authenticated-orcid":false,"given":"Xinyang","family":"Huang","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8228-2552","authenticated-orcid":false,"given":"Wenxue","family":"Li","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4687-5539","authenticated-orcid":false,"given":"Kin Fai","family":"Tse","sequence":"additional","affiliation":[{"name":"ITSC, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3131-374X","authenticated-orcid":false,"given":"Zhizhen","family":"Zhong","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4933-0276","authenticated-orcid":false,"given":"Guyue","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2736-5694","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2401-4637","authenticated-orcid":false,"given":"Xiaofeng","family":"Ye","sequence":"additional","affiliation":[{"name":"EmbedWay, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6450-8485","authenticated-orcid":false,"given":"Yiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-6028","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. 100GBASE-SR4 850nm 100m DOM MPO-12\/UPC MMF Optical Transceiver Module. https:\/\/www.fs.com\/products\/48354.html. ([n. d.])."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. 200GBASE-SR4 850nm 100m DOM MPO-12\/UPC MMF Optical Transceiver Module. https:\/\/www.fs.com\/products\/139696.html. ([n. d.])."},{"key":"e_1_3_2_1_3_1","unstructured":"[n. d.]. 400GBASE-SR4 PAM4 850nm 100m DOM MPO-12\/APC MMF Optical Transceiver Module. https:\/\/www.fs.com\/products\/226577.html. ([n. d.])."},{"key":"e_1_3_2_1_4_1","unstructured":"[n. d.]. All-to-all traffic demand collection in Megatron-LM. https:\/\/github.com\/NVIDIA\/Megatron-LM\/blob\/461b06cd6d1fb4a625cebdbca499dac9484087fc\/megatron\/core\/transformer\/moe\/token_dispatcher.py#L432. ([n. d.])."},{"key":"e_1_3_2_1_5_1","unstructured":"[n. d.]. Breakout optical cables. https:\/\/arubanetworking.hpe.com\/techdocs\/Switches\/xcvrs\/xcvr_guide\/Content\/Chp_overview\/spl-opt-cab.htm. ([n. d.])."},{"key":"e_1_3_2_1_6_1","unstructured":"[n. d.]. Calient Optical Circuit Switch. www.calient.net. ([n. d.])."},{"key":"e_1_3_2_1_7_1","unstructured":"[n. d.]. Calix\u00ae 100-04482 Compatible TAA 10GBs XGS-PON OLT XFP Transceiver with Burst Mode (SMF 1577nmTx\/1270nmRx SC N1 DOM). https:\/\/www.addonnetworks.com\/products\/transceivers\/calix\/xfp\/10gbase\/100-04482-ao. ([n. d.])."},{"key":"e_1_3_2_1_8_1","unstructured":"[n. d.]. Context parallelism overview. https:\/\/docs.nvidia.com\/megatron-core\/developer-guide\/latest\/api-guide\/context_parallel.html. ([n. d.])."},{"key":"e_1_3_2_1_9_1","unstructured":"[n. d.]. DeepSeek-V3. https:\/\/github.com\/deepseek-ai\/DeepSeek-V3\/blob\/main\/DeepSeek_V3.pdf. ([n. d.])."},{"key":"e_1_3_2_1_10_1","unstructured":"[n. d.]. DeepSpeed. https:\/\/openai.com\/index\/gpt-3-apps\/. ([n. d.])."},{"key":"e_1_3_2_1_11_1","unstructured":"[n. d.]. Doubling all2all Performance with NVIDIA Collective Communication Library 2.12. https:\/\/developer.nvidia.com\/blog\/doubling-all2all-performance-with-nvidia-collective-communication-library-2-12\/. ([n. d.])."},{"key":"e_1_3_2_1_12_1","unstructured":"[n. d.]. FlexFlow. https:\/\/github.com\/flexflow\/FlexFlow. ([n. d.])."},{"key":"e_1_3_2_1_13_1","unstructured":"[n. d.]. Generic Compatible 800GBASE-SR8 QSFP-DD PAM4 850nm 50m DOM MPO-16\/APC MMF Optical Transceiver Module. https:\/\/www.fs.com\/products\/200921.html?attribute=93760&id=3569240. ([n. d.])."},{"key":"e_1_3_2_1_14_1","unstructured":"[n. d.]. Grok. https:\/\/x.ai\/blog\/grok-1.5v. ([n. d.])."},{"key":"e_1_3_2_1_15_1","unstructured":"[n. d.]. Grok training cluster. https:\/\/www.windowscentral.com\/software-apps\/elon-musk-flaunts-the-most-powerful-training-cluster-in-the-world-that-will-transform-grok-into-the-most-powerful-ai-by-december-to-take-on-microsoft-and-openai. ([n. d.])."},{"key":"e_1_3_2_1_16_1","unstructured":"[n. d.]. htsim simulator. https:\/\/github.com\/nets-cs-pub-ro\/NDP\/wiki\/NDP-Simulator. ([n. d.])."},{"key":"e_1_3_2_1_17_1","unstructured":"[n. d.]. IPRONICS One. https:\/\/ipronics.com\/ipronics-optical-networking-engine\/. ([n. d.])."},{"key":"e_1_3_2_1_18_1","unstructured":"[n. d.]. LC UPC to LC UPC Duplex 2 Fibers. https:\/\/www.fs.com\/products\/40191.html. ([n. d.])."},{"key":"e_1_3_2_1_19_1","unstructured":"[n. d.]. LightMatter. https:\/\/lightmatter.co\/products\/passage\/. ([n. d.])."},{"key":"e_1_3_2_1_20_1","unstructured":"[n. d.]. LLaMA. https:\/\/llama.meta.com. ([n. d.])."},{"key":"e_1_3_2_1_21_1","unstructured":"[n. d.]. Mixtral 8x22B. https:\/\/huggingface.co\/mistralai\/Mixtral-8x22B-Instruct-v0.1. ([n. d.])."},{"key":"e_1_3_2_1_22_1","unstructured":"[n. d.]. Mixtral-8x7B-Instruct-v0.1. https:\/\/huggingface.co\/mistralai\/Mixtral-8x7B-Instruct-v0.1. ([n. d.])."},{"key":"e_1_3_2_1_23_1","unstructured":"[n. d.]. Mixtral of experts. https:\/\/mistral.ai\/news\/mixtral-of-experts\/. ([n. d.])."},{"key":"e_1_3_2_1_24_1","unstructured":"[n. d.]. MSN4700-WS2FC NVIDIA\u00ae Mellanox Spectrum-3 Based 32-Port Ethernet L3 Data Center Switch 32 x 400Gb QSFP-DD. https:\/\/www.colfaxdirect.com\/store\/pc\/viewPrd.asp?idproduct=4135. ([n. d.])."},{"key":"e_1_3_2_1_25_1","unstructured":"[n. d.]. Nano-Second Speed PLZT Photonics. http:\/\/epiphotonics.com\/products.html. ([n. d.])."},{"key":"e_1_3_2_1_26_1","unstructured":"[n. d.]. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl. ([n. d.])."},{"key":"e_1_3_2_1_27_1","unstructured":"[n. d.]. NVIDIA DGX SuperPOD. https:\/\/www.nvidia.com\/en-us\/data-center\/dgx-superpod\/. ([n. d.])."},{"key":"e_1_3_2_1_28_1","unstructured":"[n. d.]. NVIDIA GB200 NVL72 Delivers Trillion-Parameter LLM Training and Real-Time Inference. https:\/\/developer.nvidia.com\/blog\/nvidia-gb200-nvl72-delivers-trillion-parameter-llm-training-and-real-time-inference\/. ([n. d.])."},{"key":"e_1_3_2_1_29_1","unstructured":"[n. d.]. NVIDIA Mellanox MCX515A-CCAT ConnectX\u00ae-5 EN Network Interface Card 100GbE Single-Port QSFP28. https:\/\/www.fs.com\/products\/119648.html. ([n. d.])."},{"key":"e_1_3_2_1_30_1","unstructured":"[n. d.]. NVIDIA Mellanox MCX653105A-HDAT ConnectX\u00ae-6 InfiniBand\/VPI Adapter Card 200GbE\/HDR Single-Port QSFP56. https:\/\/www.fs.com\/products\/168437.html. ([n. d.])."},{"key":"e_1_3_2_1_31_1","unstructured":"[n. d.]. NVIDIA Mellanox MCX75310AAS-NEAT ConnectX\u00ae-7 InfiniBand\/VPI Adapter Card 400GbE\/NDR Single-Port OSFP. https:\/\/www.fs.com\/products\/212161.html. ([n. d.])."},{"key":"e_1_3_2_1_32_1","unstructured":"[n. d.]. NVIDIA Mellanox Spectrum-4 SN5600 800G 64-Port 51.2Tb\/s 2U Data Center Switch. https:\/\/fireowls.com\/products\/920-9n42f-00ri-7c0-nvidia-spectrum-sn5600-ethernet-switch?srsltid=AfmBOoqC5-OQefz1MpAi_2QkzW2tnaCTXA_xGtgoj9b3NphWUXw8dBrl. ([n. d.])."},{"key":"e_1_3_2_1_33_1","unstructured":"[n. d.]. NVIDIA NVLink and NVLink Switch. https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/. ([n. d.])."},{"key":"e_1_3_2_1_34_1","unstructured":"[n. d.]. NVIDIA NVSwitch Technical Overview. https:\/\/images.nvidia.com\/content\/pdf\/nvswitch-technical-overview.pdf. ([n. d.])."},{"key":"e_1_3_2_1_35_1","unstructured":"[n. d.]. NVIDIA Spectrum SN3700. https:\/\/marketplace.nvidia.com\/en-us\/enterprise\/networking\/sn3700\/. ([n. d.])."},{"key":"e_1_3_2_1_36_1","unstructured":"[n. d.]. NVLink Switch Specifications. https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/?ncid=no-ncid#nvlink-switch-specifications. ([n. d.])."},{"key":"e_1_3_2_1_37_1","unstructured":"[n. d.]. Polatis Optical Circuit Switch. https:\/\/www.polatis.com\/series-7000-384x384-port-software-controlled-optical-circuitswitch-sdn-enabled.asp. ([n. d.])."},{"key":"e_1_3_2_1_38_1","unstructured":"[n. d.]. Polatis Optical Switches. http:\/\/www.polatis.com\/series-7000-384x384-port-software-controlled-optical-circuit-switch-sdn-enabled.asp. ([n. d.])."},{"key":"e_1_3_2_1_39_1","unstructured":"[n. d.]. PON\/Burst-mode Transceivers. https:\/\/oesolutions.com\/product-type\/burst-mode-transceivers\/. ([n. d.])."},{"key":"e_1_3_2_1_40_1","unstructured":"[n. d.]. Qwen1.5-MoE-A2.7B. https:\/\/huggingface.co\/Qwen\/Qwen1.5-MoE-A2.7B. ([n. d.])."},{"key":"e_1_3_2_1_41_1","unstructured":"[n. d.]. Rethinking AI Architectures with Optical I\/O. https:\/\/www.windowscentral.com\/software-apps\/elon-musk-flaunts-the-most-powerful-training-cluster-in-the-world-that-will-transform-grok-into-the-most-powerful-ai-by-december-to-take-on-microsoft-and-openai. ([n. d.])."},{"key":"e_1_3_2_1_42_1","unstructured":"[n. d.]. Telescent G4 Network Topology Manager. https:\/\/www.telescent.com\/products. ([n. d.])."},{"key":"e_1_3_2_1_43_1","unstructured":"[n. d.]. XVERSE-MoE-A36B MoE base model. https:\/\/huggingface.co\/xverse\/XVERSE-MoE-A36B. ([n. d.])."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1402958.1402967"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672248"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3610862"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519935.3520020"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3406221"},{"key":"e_1_3_2_1_49_1","first-page":"820","article-title":"Optical communication substrate using glass interposer. (Oct. 24 2024)","volume":"18","author":"Bunandar Darius","year":"2024","unstructured":"Darius Bunandar, Shashank Gupta, Jessie Rosenberg, Clifford Chao, Kuang Liu, and Nicholas C Harris. 2024. Optical communication substrate using glass interposer. (Oct. 24 2024). US Patent App. 18\/638,820.","journal-title":"US Patent App."},{"key":"e_1_3_2_1_50_1","volume-title":"OSA: An Optical Switching Architecture for Data Center Networks with Unprecedented Flexibility. In 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12)","author":"Chen Kai","year":"2012","unstructured":"Kai Chen, Ankit Singla, Atul Singh, Kishore Ramachandran, Lei Xu, Yueping Zhang, Xitao Wen, and Yan Chen. 2012. OSA: An Optical Switching Architecture for Data Center Networks with Unprecedented Flexibility. In 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12). USENIX Association."},{"key":"e_1_3_2_1_51_1","volume-title":"Enabling Wide-Spread Communications on Optical Fabric with MegaSwitch. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Chen Li","year":"2017","unstructured":"Li Chen, Kai Chen, Zhonghua Zhu, Minlan Yu, George Porter, Chunming Qiao, and Shan Zhong. 2017. Enabling Wide-Spread Communications on Optical Fabric with MegaSwitch. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). USENIX Association, Boston, MA, 577\u2013593. https:\/\/www.usenix.org\/conference\/nsdi17\/technical-sessions\/presentation\/chen"},{"key":"e_1_3_2_1_52_1","volume-title":"Task-specific expert pruning for sparse mixture-of-experts. arXiv preprint arXiv:2206.00277","author":"Chen Tianyu","year":"2022","unstructured":"Tianyu Chen, Shaohan Huang, Yuan Xie, Binxing Jiao, Daxin Jiang, Haoyi Zhou, Jianxin Li, and Furu Wei. 2022. Task-specific expert pruning for sparse mixture-of-experts. arXiv preprint arXiv:2206.00277 (2022)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ECOC.2018.8535333"},{"key":"e_1_3_2_1_54_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. (2025). arXiv:cs.CL\/2501.12948 https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_1_55_1","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bin Wang Bingxuan Wang Bo Liu Chenggang Zhao Chengqi Dengr Chong Ruan Damai Dai Daya Guo Dejian Yang Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fuli Luo Guangbo Hao Guanting Chen Guowei Li H. Zhang Hanwei Xu Hao Yang Haowei Zhang Honghui Ding Huajian Xin Huazuo Gao Hui Li Hui Qu J. L. 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. J. Chen R. L. Jin Ruiqi Ge Ruizhe Pan Runxin Xu Ruyi Chen S. S. Li Shanghao Lu Shangyan Zhou Shanhuang Chen Shaoqing Wu Shengfeng Ye Shirong Ma Shiyu Wang Shuang Zhou Shuiping Yu Shunfeng Zhou Size Zheng T. Wang Tian Pei Tian Yuan Tianyu Sun W. L. Xiao Wangding Zeng Wei An Wen Liu Wenfeng Liang Wenjun Gao Wentao Zhang X. Q. Li Xiangyue Jin Xianzu Wang Xiao Bi Xiaodong Liu Xiaohan Wang Xiaojin Shen Xiaokang Chen Xiaosha Chen Xiaotao Nie Xiaowen Sun Xiaoxiang Wang Xin Liu Xin Xie Xingkai Yu Xinnan Song Xinyi Zhou Xinyu Yang Xuan Lu Xuecheng Su Y. Wu Y. K. Li Y. X. Wei Y. X. Zhu Yanhong Xu Yanping Huang Yao Li Yao Zhao Yaofeng Sun Yaohui Li Yaohui Wang Yi Zheng Yichao Zhang Yiliang Xiong Yilong Zhao Ying He Ying Tang Yishi Piao Yixin Dong Yixuan Tan Yiyuan Liu Yongji Wang Yongqiang Guo Yuchen Zhu Yuduan Wang Yuheng Zou Yukun Zha Yunxian Ma Yuting Yan Yuxiang You Yuxuan Liu Z. Z. Ren Zehui Ren Zhangli Sha Zhe Fu Zhen Huang Zhen Zhang Zhenda Xie Zhewen Hao Zhihong Shao Zhiniu Wen Zhipeng Xu Zhongyu Zhang Zhuoshu Li Zihan Wang Zihui Gu Zilin Li and Ziwei Xie. 2024. DeepSeek-V2: A Strong Economical and Efficient Mixture-of-Experts Language Model. (2024). arXiv:cs.CL\/2405.04434 https:\/\/arxiv.org\/abs\/2405.04434"},{"key":"e_1_3_2_1_56_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The Llama 3 Herd of Models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/LPT.2013.2270462"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851223"},{"key":"e_1_3_2_1_59_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_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230718.3230722"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2021.W1E.2"},{"key":"e_1_3_2_1_63_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Gibson Dan","year":"2022","unstructured":"Dan Gibson, Hema Hariharan, Eric Lance, Moray McLaren, Behnam Montazeri, Arjun Singh, Stephen Wang, Hassan MG Wassel, Zhehua Wu, Sunghwan Yoo, et al. 2022. Aquila: A unified, low-latency fabric for datacenter networks. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 1249\u20131266."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1592568.1592576"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/1592568.1592577"},{"key":"e_1_3_2_1_66_1","volume-title":"Dcell: A scalable and fault-tolerant network structure for data centers. In ACM SIGCOMM Computer Communication Review","author":"Guo Chuanxiong","year":"2010","unstructured":"Chuanxiong Guo, Hui Wu, Kai Tan, Lei Shiy, Yongguang Zhang, and Songnian Lu. 2010. Dcell: A scalable and fault-tolerant network structure for data centers. In ACM SIGCOMM Computer Communication Review, Vol. 40. ACM New York, NY, USA, 63\u201374."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626328"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486019"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488766.3488792"},{"key":"e_1_3_2_1_70_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, et al. 2024. {MegaScale}: Scaling large language model training to more than 10,000 {GPUs}. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 745\u2013760."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472900"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696348.3696856"},{"key":"e_1_3_2_1_74_1","volume-title":"Gshard: Scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668","author":"Lepikhin Dmitry","year":"2020","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim 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_75_1","volume-title":"then compress: Demystify efficient SMoe with hints from its routing policy. arXiv preprint arXiv:2310.01334","author":"Li Pingzhi","year":"2023","unstructured":"Pingzhi Li, Zhenyu Zhang, Prateek Yadav, Yi-Lin Sung, Yu Cheng, Mohit Bansal, and Tianlong Chen. 2023. Merge, then compress: Demystify efficient SMoe with hints from its routing policy. arXiv preprint arXiv:2310.01334 (2023)."},{"key":"e_1_3_2_1_76_1","unstructured":"Shen Li Yanli Zhao Rohan Varma Omkar Salpekar Pieter Noordhuis Teng Li Adam Paszke Jeff Smith Brian Vaughan Pritam Damania et al. 2020. Pytorch distributed: Experiences on accelerating data parallel training. arXiv preprint arXiv:2006.15704 (2020)."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663408.3663409"},{"key":"e_1_3_2_1_78_1","volume-title":"Moe-llava: Mixture of experts for large vision-language models. arXiv preprint arXiv:2401.15947","author":"Lin Bin","year":"2024","unstructured":"Bin Lin, Zhenyu Tang, Yang Ye, Jiaxi Cui, Bin Zhu, Peng Jin, Junwu Zhang, Munan Ning, and Li Yuan. 2024. Moe-llava: Mixture of experts for large vision-language models. arXiv preprint arXiv:2401.15947 (2024)."},{"key":"e_1_3_2_1_79_1","volume-title":"Circuit Switching Under the Radar with REACToR. In 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 14)","author":"Liu He","year":"2014","unstructured":"He Liu, Feng Lu, Alex Forencich, Rishi Kapoor, Malveeka Tewari, Geoffrey M. Voelker, George Papen, Alex C. Snoeren, and George Porter. 2014. Circuit Switching Under the Radar with REACToR. In 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 14). USENIX Association, Seattle, WA, 1\u201315. https:\/\/www.usenix.org\/conference\/nsdi14\/technical-sessions\/presentation\/liu_he"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/2716281.2836126"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604836"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604869"},{"key":"e_1_3_2_1_83_1","volume-title":"Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models. arXiv preprint arXiv:2402.14800","author":"Lu Xudong","year":"2024","unstructured":"Xudong Lu, Qi Liu, Yuhui Xu, Aojun Zhou, Siyuan Huang, Bo Zhang, Junchi Yan, and Hongsheng Li. 2024. Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models. arXiv preprint arXiv:2402.14800 (2024)."},{"key":"e_1_3_2_1_84_1","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Mellette William M","year":"2020","unstructured":"William M Mellette, Rajdeep Das, Yibo Guo, Rob McGuinness, Alex C Snoeren, and George Porter. 2020. Expanding across time to deliver bandwidth efficiency and low latency. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 1\u201318."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672273"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098838"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2016.2636025"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486007"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544265"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25841-8"},{"key":"e_1_3_2_1_93_1","volume-title":"19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25)","author":"Ren Zhenghang","year":"2025","unstructured":"Zhenghang Ren, Yuxuan Li, Zilong Wang, Xinyang Huang, Wenxue Li, Kaiqiang Xu, Xudong Liao, Yijun Sun, Bowen Liu, Han Tian, Junxue Zhang, Mingfei Wang, Zhizhen Zhong, Guyue Liu, Ying Zhang, and Kai Chen. 2025. Enabling Efficient GPU Communication over Multiple NICs with FuseLink. In 19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25). 91\u2013108."},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/OFC.2001.927572"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696348.3696860"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1364\/OPTICA.3.000064"},{"key":"e_1_3_2_1_97_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, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff 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_98_1","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. (2020). arXiv:cs.CL\/1909.08053 https:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_2_1_99_1","unstructured":"Chenchen Shou Guyue Liu Hao Nie Huaiyu Meng Yu Zhou Yimin Jiang Wenqing Lv Yelong Xu Yuanwei Lu Zhang Chen Yanbo Yu Yichen Shen Yibo Zhu and Daxin Jiang. 2025. InfiniteHBD: Building Datacenter-Scale High-Bandwidth Domain for LLM with Optical Circuit Switching Transceivers. (2025). arXiv:cs.NI\/2502.03885 https:\/\/arxiv.org\/abs\/2502.03885"},{"key":"e_1_3_2_1_100_1","volume-title":"16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Shrivastav Vishal","year":"2019","unstructured":"Vishal Shrivastav, Asaf Valadarsky, Hitesh Ballani, Paolo Costa, Ki Suh Lee, Han Wang, Rachit Agarwal, and Hakim Weatherspoon. 2019. Shoal: A network architecture for disaggregated racks. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). 255\u2013270."},{"key":"e_1_3_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787508"},{"key":"e_1_3_2_1_102_1","volume-title":"Baptiste Rozi\u00e8re, Jacob Kahn, Daniel Li, Wen-tau Yih, Jason Weston, et al.","author":"Sukhbaatar Sainbayar","year":"2024","unstructured":"Sainbayar Sukhbaatar, Olga Golovneva, Vasu Sharma, Hu Xu, Xi Victoria Lin, Baptiste Rozi\u00e8re, Jacob Kahn, Daniel Li, Wen-tau Yih, Jason Weston, et al. 2024. Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM. arXiv preprint arXiv:2403.07816 (2024)."},{"key":"e_1_3_2_1_103_1","volume-title":"arXiv preprint arXiv:2412.15115","author":"Team Qwen","year":"2024","unstructured":"Qwen Team. 2024. Qwen2.5 technical report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411029.3411037"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851222"},{"key":"e_1_3_2_1_106_1","volume-title":"Rail-only: A Low-Cost High-Performance Network for Training LLMs with Trillion Parameters.","author":"Wang Weiyang","year":"2024","unstructured":"Weiyang Wang, Manya Ghobadi, Kayvon Shakeri, Ying Zhang, and Naader Hasani. 2024. Rail-only: A Low-Cost High-Performance Network for Training LLMs with Trillion Parameters. (2024). arXiv:cs.NI\/2307.12169 https:\/\/arxiv.org\/abs\/2307.12169"},{"key":"e_1_3_2_1_107_1","volume-title":"TopoOpt: Co-optimizing Network Topology and Parallelization Strategy for Distributed Training Jobs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Wang Weiyang","year":"2023","unstructured":"Weiyang Wang, Moein Khazraee, Zhizhen Zhong, Manya Ghobadi, Zhihao Jia, Dheevatsa Mudigere, Ying Zhang, and Anthony Kewitsch. 2023. TopoOpt: Co-optimizing Network Topology and Parallelization Strategy for Distributed Training Jobs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, Boston, MA, 739\u2013767. https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/wang-weiyang"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618260.3649608"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977578.ch1"},{"key":"e_1_3_2_1_110_1","volume-title":"7th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 15)","author":"Xia Yiting","year":"2015","unstructured":"Yiting Xia, Mike Schlansker, TS Eugene Ng, and Jean Tourrilhes. 2015. Enabling Topological Flexibility for Data Centers Using {OmniSwitch}. In 7th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 15)."},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707266"},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.4.000651"},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"publisher","DOI":"10.1364\/ACPC.2017.S4C.6"},{"key":"e_1_3_2_1_114_1","volume-title":"Gemini: Practical reconfigurable datacenter networks with topology and traffic engineering. arXiv preprint arXiv:2110.08374","author":"Zhang Mingyang","year":"2021","unstructured":"Mingyang Zhang, Jianan Zhang, Rui Wang, Ramesh Govindan, Jeffrey C Mogul, and Amin Vahdat. 2021. Gemini: Practical reconfigurable datacenter networks with topology and traffic engineering. arXiv preprint arXiv:2110.08374 (2021)."},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1145\/3672201.3674121"},{"key":"e_1_3_2_1_116_1","first-page":"441","article-title":"Beam-steering system based on a MEMS-actuated vertical-coupler array. (Sept. 13 2022)","volume":"11","author":"Zhang Xiaosheng","year":"2022","unstructured":"Xiaosheng Zhang, Ming Chiang A Wu, Andrew S Michaels, and Johannes Henriksson. 2022. Beam-steering system based on a MEMS-actuated vertical-coupler array. (Sept. 13 2022). US Patent 11,441,353.","journal-title":"US Patent"},{"key":"e_1_3_2_1_117_1","volume-title":"LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training. arXiv preprint arXiv:2406.16554","author":"Zhu Tong","year":"2024","unstructured":"Tong Zhu, Xiaoye Qu, Daize Dong, Jiacheng Ruan, Jingqi Tong, Conghui He, and Yu Cheng. 2024. LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training. arXiv preprint arXiv:2406.16554 (2024). https:\/\/arxiv.org\/abs\/2406.16554"},{"key":"e_1_3_2_1_118_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Zu Yazhou","year":"2024","unstructured":"Yazhou Zu, Alireza Ghaffarkhah, Hoang-Vu Dang, Brian Towles, Steven Hand, Safeen Huda, Adekunle Bello, Alexander Kolbasov, Arash Rezaei, Dayou Du, et al. 2024. Resiliency at Scale: Managing {Google's}{TPUv4} Machine Learning Supercomputer. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 761\u2013774."}],"event":{"name":"SIGCOMM '25: ACM SIGCOMM 2025 Conference","location":"S\u00e3o Francisco Convent Coimbra Portugal","acronym":"SIGCOMM '25","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2025 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3718958.3750465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:55:46Z","timestamp":1756313746000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718958.3750465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":118,"alternative-id":["10.1145\/3718958.3750465","10.1145\/3718958"],"URL":"https:\/\/doi.org\/10.1145\/3718958.3750465","relation":{},"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"2025-08-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}