{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:57:16Z","timestamp":1777460236353,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":10,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3805621.3807647","type":"proceedings-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:08:45Z","timestamp":1777381725000},"page":"232-237","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Accelerating Local LLMs on Resource-Constrained Edge Devices via Distributed Prompt Caching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-3842","authenticated-orcid":false,"given":"Hiroki","family":"Matsutani","sequence":"first","affiliation":[{"name":"Keio University, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9715-8603","authenticated-orcid":false,"given":"Naoki","family":"Matsuda","sequence":"additional","affiliation":[{"name":"Keio University, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5970-9422","authenticated-orcid":false,"given":"Naoto","family":"Sugiura","sequence":"additional","affiliation":[{"name":"Keio University, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the USENIX Annual Technical Conference (ATC'24)","author":"Gao Bin","year":"2024","unstructured":"Bin Gao, Zhuomin He, Puru Sharma, Qingxuan Kang, Djordje Jevdjic, Junbo Deng, Xingkun Yang, Zhou Yu, and Pengfei Zuo. 2024. Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention. In Proceedings of the USENIX Annual Technical Conference (ATC'24). 111\u2013126."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the Annual Conference on Machine Learning and Systems (MLSys'24)","author":"Gim In","year":"2024","unstructured":"In Gim, Guojun Chen, Seung-Seob Lee, Nikhil Sarda, Anurag Khandelwal, and Lin Zhong. 2024. Prompt Cache: Modular Attention Reuse for Low-Latency Inference. In Proceedings of the Annual Conference on Machine Learning and Systems (MLSys'24). 325\u2013338."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR'21)","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Understanding. In Proceedings of the International Conference on Learning Representations (ICLR'21)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672274"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Annual Conference on Machine Learning and Systems (MLSys'23)","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. In Proceedings of the Annual Conference on Machine Learning and Systems (MLSys'23). 606\u2013624."},{"key":"e_1_3_2_1_7_1","unstructured":"Sajal Regmi and Chetan Phakami Pun. 2024. GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching. arXiv:2411.05276"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS'17)","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. In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS'17)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.623"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS'24)","author":"Zheng Lianmin","year":"2024","unstructured":"Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng. 2024. SGLang: Efficient Execution of Structured Language Model Programs. In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS'24)."}],"event":{"name":"EuroSys '26: 21st European Conference on Computer Systems","location":"Edinburgh Scotland Uk","acronym":"EuroMLSys '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Sixth European Workshop on Machine Learning and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805621.3807647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:11:53Z","timestamp":1777381913000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805621.3807647"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":10,"alternative-id":["10.1145\/3805621.3807647","10.1145\/3805621"],"URL":"https:\/\/doi.org\/10.1145\/3805621.3807647","relation":{},"subject":[],"published":{"date-parts":[[2026,4,27]]},"assertion":[{"value":"2026-04-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}