{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:27:57Z","timestamp":1786476477924,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":15,"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\/3789240.3828738","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"1988-1993","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GPU-Centric Stateless LLM Serving With GIGANETS"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3410-8621","authenticated-orcid":false,"given":"Xiaoliang","family":"Wang","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5893-2828","authenticated-orcid":false,"given":"Zhenwei","family":"Pi","sequence":"additional","affiliation":[{"name":"Tensorfer, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5142-6453","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tensorfer, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8497-3739","authenticated-orcid":false,"given":"Camtu","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, 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":"Xin Cheng Wangding Zeng Damai Dai Qinyu Chen Bingxuan Wang Zhenda Xie Kezhao Huang Xingkai Yu Zhewen Hao Yukun Li Han Zhang Huishuai Zhang Dongyan Zhao and Wenfeng Liang. 2026. Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models. (2026). arXiv:cs.CL\/2601.07372 https:\/\/arxiv.org\/abs\/2601.07372"},{"key":"e_1_3_2_1_2_1","volume-title":"The State of AI Infrastructure at Scale","author":"ML.","year":"2024","unstructured":"ClearML. 2024. The State of AI Infrastructure at Scale 2024. (2024). https:\/\/ai-infrastructure.org\/wp-content\/uploads\/2024\/03\/The-State-of-AI-Infrastructure-at-Scale-2024.pdf"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI","author":"Fu Yao","year":"2024","unstructured":"Yao Fu, Leyang Xue, Yeqi Huang, Andrei-Octavian Brabete, Dmitrii Ustiugov, Yuvraj Patel, and Luo Mai. 2024. ServerlessLLM: Low-Latency Serverless Inference for Large Language Models. In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2024). USENIX Association, Santa Clara, CA, USA."},{"key":"e_1_3_2_1_4_1","volume-title":"MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool. arXiv preprint","author":"Hu Cunchen","year":"2024","unstructured":"Cunchen Hu, Heyang Huang, Junhao Hu, Jiang Xu, Xusheng Chen, Tao Xie, Chenxi Wang, Sa Wang, Yungang Bao, Ninghui Sun, and Yizhou Shan. 2024. MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool. arXiv preprint (2024). arXiv:2406.17565 https:\/\/arxiv.org\/abs\/2406.17565"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731569.3764857"},{"key":"e_1_3_2_1_6_1","unstructured":"Yuhan Liu Yihua Cheng Jiayi Yao Yuwei An Xiaokun Chen Shaoting Feng Yuyang Huang Samuel Shen Rui Zhang Kuntai Du and Junchen Jiang. 2025. LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference. (2025). arXiv:cs.LG\/2510.09665 https:\/\/arxiv.org\/abs\/2510.09665"},{"key":"e_1_3_2_1_7_1","volume-title":"Introducing NVIDIA BlueField-4-Powered Inference Context Memory Storage Platform for the Next Frontier of AI. (Jan","author":"NVIDIA Corporation","year":"2026","unstructured":"NVIDIA Corporation. 2026. Introducing NVIDIA BlueField-4-Powered Inference Context Memory Storage Platform for the Next Frontier of AI. (Jan. 2026). https:\/\/www.nvidia.com\/en-us\/events\/ces\/"},{"key":"e_1_3_2_1_8_1","unstructured":"SGLang Project. 2025. SGLang: Fast Serving Framework for Large Language Models. https:\/\/github.com\/sgl-project\/sglang. (2025). Accessed: 2026-01-30."},{"key":"e_1_3_2_1_9_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 \u2014 A KVCache-centric Architecture for Serving LLM Chatbot. In 23rd USENIX Conference on File and Storage Technologies (FAST 25). USENIX Association, Santa Clara, CA."},{"key":"e_1_3_2_1_10_1","volume-title":"Redis: In-Memory Data Structure Store. Technical Report","author":"Sanfilippo Salvatore","year":"2009","unstructured":"Salvatore Sanfilippo and Pieter Noordhuis. 2009. Redis: In-Memory Data Structure Store. Technical Report. Redis Ltd. https:\/\/redis.io"},{"key":"e_1_3_2_1_11_1","unstructured":"vLLM Project. 2025. vLLM: Very Large Language Model Serving. https:\/\/github.com\/vllm-project\/vllm. (2025). Accessed: 2025-12-25."},{"key":"e_1_3_2_1_12_1","volume-title":"Aegaeon: Effective GPU Pooling for Concurrent LLM Serving on the Market. In ACM SIGOPS Symposium on Operating Systems Principles (SOSP).","author":"Xiang Yuxing","year":"2025","unstructured":"Yuxing Xiang, Xue Li, Kun Qian, Yufan Yang, Diwen Zhu, Wenyuan Yu, Ennan Zhai, Xuanzhe Liu, Xin Jin, and Jingren Zhou. 2025. Aegaeon: Effective GPU Pooling for Concurrent LLM Serving on the Market. In ACM SIGOPS Symposium on Operating Systems Principles (SOSP)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3786627"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI","author":"Zhang Dingyan","year":"2025","unstructured":"Dingyan Zhang, Haotian Wang, Yang Liu, Xingda Wei, Yizhou Shan, Rong Chen, and Haibo Chen. 2025. BlitzScale: Fast and Live Large Model Autoscaling with O(1) Host Caching. In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2025). Santa Clara, CA, USA."},{"key":"e_1_3_2_1_15_1","volume-title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI).","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 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI)."}],"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\/3789240.3828738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:40:33Z","timestamp":1786473633000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3828738"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":15,"alternative-id":["10.1145\/3789240.3828738","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3828738","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"}}]}}