{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:27:49Z","timestamp":1786476469557,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":38,"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\/3789240.3829152","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"505-518","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Connecting 100K+ GPUs: Building the Communication Stack for Large-Scale LLM Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4205-4678","authenticated-orcid":false,"given":"Hongyi","family":"Zeng","sequence":"first","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0208-096X","authenticated-orcid":false,"given":"Min","family":"Si","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7390-117X","authenticated-orcid":false,"given":"Pavan","family":"Balaji","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3649-9195","authenticated-orcid":false,"given":"Yongzhou","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6752-3135","authenticated-orcid":false,"given":"Ching-Hsiang","family":"Chu","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9050-0444","authenticated-orcid":false,"given":"Adithya","family":"Gangidi","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4794-9971","authenticated-orcid":false,"given":"Prashanth","family":"Kannan","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5439-9379","authenticated-orcid":false,"given":"Bingzhe","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4243-4137","authenticated-orcid":false,"given":"Saif","family":"Hasan","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4698-7915","authenticated-orcid":false,"given":"Dong","family":"He","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5945-8063","authenticated-orcid":false,"given":"Deep","family":"Shah","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9220-8353","authenticated-orcid":false,"given":"Ashmitha Jeevaraj","family":"Shetty","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9895-0191","authenticated-orcid":false,"given":"Gregory R","family":"Steinbrecher","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6230-9396","authenticated-orcid":false,"given":"Srikanth","family":"Sundaresan","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5880-6092","authenticated-orcid":false,"given":"Yulun","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0229-6220","authenticated-orcid":false,"given":"Yexin","family":"Wu","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3766-9472","authenticated-orcid":false,"given":"Mingran","family":"Yang","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2483-0062","authenticated-orcid":false,"given":"Kenny","family":"Yu","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2381-0212","authenticated-orcid":false,"given":"Minlan","family":"Yu","sequence":"additional","affiliation":[{"name":"Harvard, Cambridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9427-7654","authenticated-orcid":false,"given":"Cen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3904-8725","authenticated-orcid":false,"given":"Shengbao","family":"Zheng","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0369-218X","authenticated-orcid":false,"given":"Wesley","family":"Bland","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4535-7826","authenticated-orcid":false,"given":"Denis","family":"Boyda","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4686-4491","authenticated-orcid":false,"given":"Suman","family":"Gumudavelli","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3413-5357","authenticated-orcid":false,"given":"Subodh","family":"Iyengar","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7717-5640","authenticated-orcid":false,"given":"Daniel","family":"Johnson","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8528-602X","authenticated-orcid":false,"given":"Cristian","family":"Lumezanu","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2666-432X","authenticated-orcid":false,"given":"Kai","family":"Luo","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1436-2374","authenticated-orcid":false,"given":"Rui","family":"Miao","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6650-6141","authenticated-orcid":false,"given":"Zhe","family":"Qu","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3029-5005","authenticated-orcid":false,"given":"Venkatraghavan","family":"Ramesh","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2448-0873","authenticated-orcid":false,"given":"Jingliang","family":"Ren","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6094-7567","authenticated-orcid":false,"given":"Maxim","family":"Samoylov","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3251-5642","authenticated-orcid":false,"given":"Jan","family":"Seidel","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0885-4865","authenticated-orcid":false,"given":"Qiye","family":"Tan","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7181-3293","authenticated-orcid":false,"given":"Feng","family":"Tian","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7285-6682","authenticated-orcid":false,"given":"Xinfeng","family":"Xie","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5733-7808","authenticated-orcid":false,"given":"Jingyi","family":"Yang","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1791-6325","authenticated-orcid":false,"given":"Yimeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5621-8247","authenticated-orcid":false,"given":"Shuqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"N\/A, Menlo Park, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7354-8042","authenticated-orcid":false,"given":"Tiane Art","family":"Zhu","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, USA"}],"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":"10.1145\/3646547.3689028"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2018.08.002"},{"key":"e_1_3_2_1_3_1","unstructured":"DeepSeek. 2025. DeepEP Communication Library. https:\/\/github.com\/deepseekai\/DeepEP."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation","author":"Deng Yangtao","year":"2025","unstructured":"Yangtao Deng, Xiang Shi, Zhuo Jiang, Xingjian Zhang, Lei Zhang, Zhang Zhang, Bo Li, Zuquan Song, Hang Zhu, Gaohong Liu, Fuliang Li, Shuguang Wang, Haibin Lin, Jianxi Ye, and Minlan Yu. 2025. Minder: faulty machine detection for large-scale distributed model training. In Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation (Philadelphia, PA, USA) (NSDI '25). USENIX Association, USA, Article 27, 17 pages."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731569.3764848"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation","author":"Dong Jianbo","year":"2025","unstructured":"Jianbo Dong, Kun Qian, Pengcheng Zhang, Zhilong Zheng, Liang Chen, Fei Feng, Yichi Xu, Yikai Zhu, Gang Lu, Xue Li, Zhihui Ren, Zhicheng Wang, Bin Luo, Peng Zhang, Yang Liu, Yanqing Chen, Yu Guan, Weicheng Wang, Chaojie Yang, Yang Zhang, Man Yuan, Hanyu Zhao, Yong Li, Zihan Zhao, Shan Li, Xianlong Zeng, Zhiping Yao, Binzhang Fu, Ennan Zhai, Wei Lin, Chao Wang, and Dennis Cai. 2025. Evolution of Aegis: fault diagnosis for AI model training service in production. In Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation (Philadelphia, PA, USA) (NSDI '25). USENIX Association, USA, Article 46, 17 pages."},{"key":"e_1_3_2_1_7_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. J. Mach. Learn. Res. 23 (2022), 120:1\u2013120:39. https:\/\/jmlr.org\/papers\/v23\/21-0998.html","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3730567.3764494"},{"key":"e_1_3_2_1_10_1","unstructured":"Yu Guan Zhiyu Yin Haoyu Chen Sheng Cheng Chaojie Yang Kun Qian Tianyin Xu Yang Zhang Hanyu Zhao Yong Li Wei Lin Dennis Cai and Ennan Zhai. 2025. PerfTracker: Online Performance Troubleshooting for Large-scale Model Training in Production. arXiv:2506.08528 [cs.DC] https:\/\/arxiv.org\/abs\/2506.08528"},{"key":"e_1_3_2_1_11_1","unstructured":"Saif Hasan. 2025. NCCL Fast Init - CPU Optimizations for NCCL Initialization Large Scale. https:\/\/github.com\/NVIDIA\/nccl\/pull\/1789."},{"key":"e_1_3_2_1_12_1","unstructured":"Saif Hasan. 2025. NCCL Fast Init - Improve Bootstrap AllGather by 2x at large scale. https:\/\/github.com\/NVIDIA\/nccl\/pull\/1791."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation","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, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, and Xin Liu. 2024. MegaScale: scaling large language model training to more than 10,000 GPUs. In Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation (Santa Clara, CA, USA) (NSDI'24). USENIX Association, USA, Article 41, 16 pages."},{"key":"e_1_3_2_1_14_1","unstructured":"Mohan Kalkunte Niranjan Vaidya and Pete Del Vecchio. 2023. Cognitive routing in the Tomahawk 5 data center switch. https:\/\/www.broadcom.com\/blog\/cognitive-routing-in-the-tomahawk-5-data-center-switch."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750514"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672249"},{"key":"e_1_3_2_1_17_1","unstructured":"Meta. 2024. Grand Teton. https:\/\/www.opencompute.org\/documents\/grand-tetonintel-based-cpu-tray-specification-v1-0-pdf."},{"key":"e_1_3_2_1_18_1","unstructured":"Elon Musk. 2026. Colossus 2 supercomputer. https:\/\/x.com\/elonmusk\/status\/2012500968571637891."},{"key":"e_1_3_2_1_19_1","unstructured":"Amazon News. 2025. AWS activates Project Rainier: One of the world's largest AI compute clusters comes online. https:\/\/www.aboutamazon.com\/news\/aws\/aws-project-rainier-ai-trainium-chips-compute-cluster\/."},{"key":"e_1_3_2_1_20_1","unstructured":"NVIDIA. 2024. NVLink. https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/."},{"key":"e_1_3_2_1_21_1","unstructured":"Nvidia. 2025. NVIDIA Inference Xfer Library (NIXL). hhttps:\/\/github.com\/aidynamo\/nixl."},{"key":"e_1_3_2_1_22_1","unstructured":"NVIDIA Corporation. 2025. Fusing Communication and Compute with New Device API and Copy Engine Collectives in NVIDIA NCCL 2.28. https:\/\/developer.nvidia.com\/blog\/fusing-communication-and-compute-with-new-deviceapi-and-copy-engine-collectives-in-nvidia-nccl-2-28\/."},{"key":"e_1_3_2_1_23_1","unstructured":"NVIDIA Corporation. 2025. New Scaling Algorithm and Initialization with NVIDIA Collective Communications Library 2.23. https:\/\/developer.nvidia.com\/blog\/new-scaling-algorithm-and-initialization-with-nvidia-collective-communications-library-2-23\/."},{"key":"e_1_3_2_1_24_1","unstructured":"OpenAI. 2025. OpenAI Oracle and SoftBank expand Stargate with five new AI data center sites. https:\/\/openai.com\/index\/five-new-stargate-sites\/."},{"key":"e_1_3_2_1_25_1","unstructured":"PyTorch. 2025. Torchft Documentation. https:\/\/github.com\/meta-pytorch\/torchft."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750527"},{"key":"e_1_3_2_1_27_1","volume-title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving. arXiv:2407.00079 [cs.DC] https:\/\/arxiv.org\/abs\/2407.00079","author":"Qin Ruoyu","year":"2025","unstructured":"Ruoyu Qin, Zheming Li, Weiran He, Mingxing Zhang, Yongwei Wu, Weimin Zheng, and Xinran Xu. 2025. Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving. arXiv:2407.00079 [cs.DC] https:\/\/arxiv.org\/abs\/2407.00079"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI '23)","author":"Shah Aashaka","year":"2023","unstructured":"Aashaka Shah, Vijay Chidambaram, Meghan Cowan, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Jacob Nelson, and Olli Saarikivi. 2023. MSCCL: Microsoft Collective Communication Library. In Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI '23). USENIX Association, Boston, MA, 833\u2013846."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI '23)","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 Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI '23). USENIX Association, Boston, MA, 817\u2013831."},{"key":"e_1_3_2_1_30_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. arXiv:1909.08053 [cs.CL] https:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_2_1_31_1","unstructured":"Min Si Pavan Balaji Yongzhou Chen Ching-Hsiang Chu Adi Gangidi Saif Hasan Subodh Iyengar Dan Johnson Bingzhe Liu Regina Ren Ashmitha Jeevaraj Shetty Greg Steinbrecher Yulun Wang Bruce Wu Xinfeng Xie Jingyi Yang Mingran Yang Kenny Yu Minlan Yu Cen Zhao Wes Bland Denis Boyda Suman Gumudavelli Prashanth Kannan Cristian Lumezanu Rui Miao Zhe Qu Venkat Ramesh Maxim Samoylov Jan Seidel Srikanth Sundaresan Feng Tian Qiye Tan Shuqiang Zhang Yimeng Zhao Shengbao Zheng Art Zhu and Hongyi Zeng. 2025. Collective Communication for 100k+ GPUs. arXiv:2510.20171 [cs.DC] https:\/\/arxiv.org\/abs\/2510.20171"},{"key":"e_1_3_2_1_32_1","unstructured":"Yee Jiun Song and Kaushik Veeraraghavan. 2025. Meta's Infrastructure Evolution and the Advent of AI. https:\/\/engineering.fb.com\/2025\/09\/29\/data-infrastructure\/metas-infrastructure-evolution-and-the-advent-of-ai\/."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750505"},{"key":"e_1_3_2_1_34_1","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Wang Xizheng","unstructured":"Xizheng Wang, Qingxu Li, Yichi Xu, Gang Lu, Dan Li, Li Chen, Heyang Zhou, Linkang Zheng, Sen Zhang, Yikai Zhu, Yang Liu, Pengcheng Zhang, Kun Qian, Kunling He, Jiaqi Gao, Ennan Zhai, Dennis Cai, and Binzhang Fu. 2025. SimAI: Unifying Architecture Design and Performance Tuning for Large-Scale Large Language Model Training with Scalability and Precision. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). USENIX Association, Philadelphia, PA, 541\u2013558. https:\/\/www.usenix.org\/conference\/nsdi25\/presentation\/wang-xizheng-simai"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS57527.2023.00035"},{"key":"e_1_3_2_1_36_1","unstructured":"Xiguang Wu. 2022. Reducing job completion time in AI\/ML clusters. https:\/\/www.broadcom.com\/blog\/reducing-job-completion-time-in-ai-ml-clusters."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"},{"key":"e_1_3_2_1_38_1","volume-title":"Jiaqi Gao, Yilong Zhao, Yongji Wu, Kaichao You, Fengyuan Ren, Zhiying Xu, Costin Raiciu, and Ion Stoica.","author":"Zhou Yang","year":"2025","unstructured":"Yang Zhou, Zhongjie Chen, Ziming Mao, ChonLam Lao, Shuo Yang, Pravein Govindan Kannan, Jiaqi Gao, Yilong Zhao, Yongji Wu, Kaichao You, Fengyuan Ren, Zhiying Xu, Costin Raiciu, and Ion Stoica. 2025. An Extensible Software Transport Layer for GPU Networking. arXiv:2504.17307 [cs.NI] https:\/\/arxiv.org\/abs\/2504.17307"}],"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\/3789240.3829152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:39:49Z","timestamp":1786473589000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3829152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":38,"alternative-id":["10.1145\/3789240.3829152","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3829152","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"}}]}}