{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:43:49Z","timestamp":1760057029499,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB2906601"],"award-info":[{"award-number":["2024YFB2906601"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3748273.3749196","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T16:19:34Z","timestamp":1756829974000},"page":"5-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["RTT- or Bandwidth-Bound? Demystifying the KV Cache Transfer in Large Language Model Serving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1002-4789","authenticated-orcid":false,"given":"Shengnan","family":"Yue","sequence":"first","affiliation":[{"name":"China Mobile Research Institute, China Mobile"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9085-2247","authenticated-orcid":false,"given":"Mowei","family":"Wang","sequence":"additional","affiliation":[{"name":"DataCom Production Line, Huawei Technologies"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9986-917X","authenticated-orcid":false,"given":"Yu","family":"Yan","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, China Mobile"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4459-8847","authenticated-orcid":false,"given":"Weiqiang","family":"Cheng","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, China Mobile"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0632-7402","authenticated-orcid":false,"given":"Zihan","family":"Jiang","sequence":"additional","affiliation":[{"name":"DataCom Production Line, Huawei Technologies"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9381-2019","authenticated-orcid":false,"given":"Zhenhui","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, China Mobile and Department of Computer Science and Technology, Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.54"},{"key":"e_1_3_2_1_2_1","volume-title":"Levine (Eds.)","volume":"36","author":"Borzunov Alexander","year":"2023","unstructured":"Alexander Borzunov, Max Ryabinin, Artem Chumachenko, Dmitry Baranchuk, Tim Dettmers, Younes Belkada, Pavel Samygin, and Colin A Raffel. 2023. Distributed Inference and Fine-tuning of Large Language Models Over The Internet. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 12312--12331. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/28bf1419b9a1f908c15f6195f58cb865-Paper-Conference.pdf"},{"key":"e_1_3_2_1_3_1","unstructured":"Huawei. 2025. MindIE. https:\/\/www.hiascend.com\/en\/software\/mindie."},{"key":"e_1_3_2_1_4_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Jain Paras","year":"2023","unstructured":"Paras Jain, Sam Kumar, Sarah Wooders, Shishir G Patil, Joseph E Gonzalez, and Ion Stoica. 2023. Skyplane: Optimizing transfer cost and throughput using {Cloud-Aware} overlays. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 1375--1389."},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Machine Learning. PMLR, 21946--21961","author":"Jiang Youhe","year":"2024","unstructured":"Youhe Jiang, Ran Yan, Xiaozhe Yao, Yang Zhou, Beidi Chen, and Binhang Yuan. 2024. HexGen: Generative Inference of Large Language Model over Heterogeneous Environment. In International Conference on Machine Learning. PMLR, 21946--21961."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_7_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717459"},{"key":"e_1_3_2_1_9_1","unstructured":"Nvidia. 2025. Nvidia dynamo. https:\/\/developer.nvidia.com\/blog\/introducingnvidia-dynamo-a-low-latency-distributed-inference-framework-for-scaling-reasoning-ai-models\/."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_2_1_11_1","first-page":"606","article-title":"Efficiently scaling transformer inference","volume":"5","author":"Pope Reiner","year":"2023","unstructured":"Reiner Pope, Sholto Douglas, Aakanksha Chowdhery, Jacob Devlin, James Bradbury, Jonathan Heek, Kefan Xiao, Shivani Agrawal, and Jeff Dean. 2023. Efficiently scaling transformer inference. Proceedings of Machine Learning and Systems 5 (2023), 606--624.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_12_1","volume-title":"23rd USENIX Conference on File and Storage Technologies (FAST 25)","author":"Qin Ruoyu","year":"2025","unstructured":"Ruoyu Qin, Zheming Li, Weiran He, Jialei Cui, Feng Ren, Mingxing Zhang, Yongwei Wu, Weimin Zheng, and Xinran Xu. 2025. Mooncake: Trading More Storage for Less Computation---A {KVCache-centric} Architecture for Serving {LLM} Chatbot. In 23rd USENIX Conference on File and Storage Technologies (FAST 25). 155--170."},{"key":"e_1_3_2_1_13_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_15_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Yang Zongheng","year":"2023","unstructured":"Zongheng Yang, Zhanghao Wu, Michael Luo, Wei-Lin Chiang, Romil Bhardwaj, Woosuk Kwon, Siyuan Zhuang, Frank Sifei Luan, Gautam Mittal, Scott Shenker, et al. 2023. {SkyPilot}: An intercloud broker for sky computing. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 437--455."},{"key":"e_1_3_2_1_16_1","volume-title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhong Yinmin","year":"2024","unstructured":"Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, and Hao Zhang. 2024. DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 193--210. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/zhong-yinmin"}],"event":{"name":"SIGCOMM '25: ACM SIGCOMM 2025 Conference","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"],"location":"Coimbra Portugal","acronym":"SIGCOMM '25"},"container-title":["Proceedings of the 2nd Workshop on Networks for AI Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748273.3749196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T14:11:18Z","timestamp":1760019078000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748273.3749196"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":16,"alternative-id":["10.1145\/3748273.3749196","10.1145\/3748273"],"URL":"https:\/\/doi.org\/10.1145\/3748273.3749196","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-09-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}