{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:28:08Z","timestamp":1786476488025,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":18,"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-nc-nd\/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\/3789240.3829347","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"2077-2082","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DynamoServe: A Distributed Tiered Memory System for Multi-tenant LLM Serving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3664-4484","authenticated-orcid":false,"given":"Diman","family":"Zad Tootaghaj","sequence":"first","affiliation":[{"name":"Networking and Distributed Systems Lab, Hewlett Packard Enterprise Labs, Milpitas, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1986-5104","authenticated-orcid":false,"given":"Khaled","family":"Diab","sequence":"additional","affiliation":[{"name":"Hewlett Packard Enterprise Labs, Vancouver, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8622-9493","authenticated-orcid":false,"given":"Bob","family":"Lantz","sequence":"additional","affiliation":[{"name":"Networking and Distributed Systems Lab, Hewlett Packard Enterprise Labs, Milpitas, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3718-5272","authenticated-orcid":false,"given":"Hanjiang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electrical & Computer Engineering, Georgia Tech, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1849-5155","authenticated-orcid":false,"given":"K. K.","family":"Ramakrishnan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9552-5381","authenticated-orcid":false,"given":"Md Ashfaqur","family":"Rahaman","sequence":"additional","affiliation":[{"name":"Scalable Software Systems Lab, University of Utah, Salt Lake City, UT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5446-9603","authenticated-orcid":false,"given":"Ryan","family":"Stutsman","sequence":"additional","affiliation":[{"name":"Scalable Software Systems Lab, University of Utah, Salt Lake City, UT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4594-8164","authenticated-orcid":false,"given":"Puneet","family":"Sharma","sequence":"additional","affiliation":[{"name":"Networking and Distributed Systems Lab, Hewlett Packard Enterprise Labs, Milpitas, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5738-6942","authenticated-orcid":false,"given":"Tushar","family":"Krishna","sequence":"additional","affiliation":[{"name":"School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"CXL Consortium. 2022. Compute Express Link (CXL): Enabling Memory Disaggregation. https:\/\/www.computeexpresslink.org."},{"key":"e_1_3_2_1_2_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Gu Juncheng","year":"2017","unstructured":"Juncheng Gu, Youngmoon Lee, Yiwen Zhang, Mosharaf Chowdhury, and Kang G Shin. 2017. Efficient memory disaggregation with infiniswap. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 649\u2013667."},{"key":"e_1_3_2_1_3_1","volume-title":"Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al.","author":"Hoffmann Jordan","year":"2022","unstructured":"Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al. 2022. Training compute-optimal large language models. arXiv preprint arXiv:2203.15556 (2022)."},{"key":"e_1_3_2_1_4_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Li Zhuohan","year":"2023","unstructured":"Zhuohan Li, Lianmin Zheng, Yinmin Zhong, Vincent Liu, Ying Sheng, Xin Jin, Yanping Huang, Zhifeng Chen, Hao Zhang, Joseph E Gonzalez, et al. 2023. {AlpaServe}: Statistical multiplexing with model parallelism for deep learning serving. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 663\u2013679."},{"key":"e_1_3_2_1_6_1","volume-title":"Disaggregated memory for expansion and sharing in blade servers. ACM SIGARCH computer architecture news 37, 3","author":"Lim Kevin","year":"2009","unstructured":"Kevin Lim, Jichuan Chang, Trevor Mudge, Parthasarathy Ranganathan, Steven K Reinhardt, and Thomas F Wenisch. 2009. Disaggregated memory for expansion and sharing in blade servers. ACM SIGARCH computer architecture news 37, 3 (2009), 267\u2013278."},{"key":"e_1_3_2_1_7_1","unstructured":"NVIDIA Corporation. 2018. NVLink High-Speed GPU Interconnect. https:\/\/images.nvidia.com\/content\/pdf\/dgx1-system-architecture-whitepaper1.pdf."},{"key":"e_1_3_2_1_8_1","volume-title":"Dark: Fragmentation, Fairness, and Efficiency in GPUs. In USENIX OSDI.","author":"James Percival","year":"2023","unstructured":"James Percival et al. 2023. Inference in the Dark: Fragmentation, Fairness, and Efficiency in GPUs. In USENIX OSDI."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of machine learning and systems 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\u2013624."},{"key":"e_1_3_2_1_10_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_11_1","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. {Zero-offload}: Democratizing {billion-scale} model training. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). 551\u2013564."},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Machine Learning. PMLR, 31094\u201331116","author":"Sheng Ying","year":"2023","unstructured":"Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Beidi Chen, Percy Liang, Christopher R\u00e9, Ion Stoica, and Ce Zhang. 2023. Flexgen: High-throughput generative inference of large language models with a single gpu. In International Conference on Machine Learning. PMLR, 31094\u201331116."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","volume":"2","author":"Kumar Abhishek Vijaya","year":"2025","unstructured":"Abhishek Vijaya Kumar, Gianni Antichi, and Rachee Singh. 2025. Aqua: Network-Accelerated Memory Offloading for LLMs in Scale-Up GPU Domains. In Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2. 48\u201362."},{"key":"e_1_3_2_1_14_1","volume-title":"d.]. vllm Github,. https:\/\/github.com\/vllm-project\/vllm. [Online","year":"2025","unstructured":"vllm Github. [n. d.]. vllm Github,. https:\/\/github.com\/vllm-project\/vllm. [Online; accessed 2025]."},{"key":"e_1_3_2_1_15_1","unstructured":"Tong Wu Fuchun Yang Wencong Zhang Xiaohui Liu et al. 2023. AntMan: Dynamic scaling on GPU clusters with guarantees. In USENIX NSDI."},{"key":"e_1_3_2_1_16_1","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A distributed serving system for {Transformer-Based} generative models. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 521\u2013538."},{"key":"e_1_3_2_1_17_1","volume-title":"Alnaas: Efficient Multi-Tenant GPU Sharing for Neural Network Inference. In USENIX ATC.","author":"Zhang Jiawei","year":"2022","unstructured":"Jiawei Zhang, Zhenhua Jin, Wenjun Xu, et al. 2022. Alnaas: Efficient Multi-Tenant GPU Sharing for Neural Network Inference. In USENIX ATC."},{"key":"e_1_3_2_1_18_1","first-page":"162","article-title":"Hetegen: Efficient heterogeneous parallel inference for large language models on resource-constrained devices","volume":"6","author":"Zhao Xuanlei","year":"2024","unstructured":"Xuanlei Zhao, Bin Jia, Haotian Zhou, Ziming Liu, Shenggan Cheng, and Yang You. 2024. Hetegen: Efficient heterogeneous parallel inference for large language models on resource-constrained devices. Proceedings of Machine Learning and Systems 6 (2024), 162\u2013172.","journal-title":"Proceedings of Machine Learning and Systems"}],"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\/3789240.3829347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:45:14Z","timestamp":1786473914000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3829347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":18,"alternative-id":["10.1145\/3789240.3829347","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3829347","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"}}]}}