{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T15:03:40Z","timestamp":1779807820438,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":9,"publisher":"ACM","funder":[{"name":"National Science Foundation","award":["2315851"],"award-info":[{"award-number":["2315851"]}]},{"name":"Virginia Tech College of Engineering","award":["Major Grants Initiative Program"],"award-info":[{"award-number":["Major Grants Initiative Program"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,8]]},"DOI":"10.1145\/3801489.3806912","type":"proceedings-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T14:22:48Z","timestamp":1779805368000},"page":"28-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5293-5348","authenticated-orcid":false,"given":"Xiangchen","family":"Li","sequence":"first","affiliation":[{"name":"Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4563-8697","authenticated-orcid":false,"given":"Jiakun","family":"Fan","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7879-4328","authenticated-orcid":false,"given":"Qingyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"University College Dublin, Dublin, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0157-7173","authenticated-orcid":false,"given":"Dimitrios","family":"Spatharakis","sequence":"additional","affiliation":[{"name":"National Technical University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3799-5702","authenticated-orcid":false,"given":"Saeid","family":"Ghafouri","sequence":"additional","affiliation":[{"name":"Queen's University Belfast, Belfast, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5868-9259","authenticated-orcid":false,"given":"Hans","family":"Vandierendonck","sequence":"additional","affiliation":[{"name":"Queens University Belfast, Belfast, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6139-1100","authenticated-orcid":false,"given":"Deepu","family":"John","sequence":"additional","affiliation":[{"name":"University College Dublin, Dublin, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0149-7509","authenticated-orcid":false,"given":"Bo","family":"Ji","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0871-7263","authenticated-orcid":false,"given":"Ali R.","family":"Butt","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0217-8307","authenticated-orcid":false,"given":"Dimitrios","family":"Nikolopoulos","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/67d57c32e20fd0a7a302cb81d36e40d5-Abstract-Conference.html"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 5th Conference on Machine Learning and Systems (MLSys 2024","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 5th Conference on Machine Learning and Systems (MLSys 2024). Santa Clara, CA, USA. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2024\/file\/a66caa1703fe34705a4368c3014c1966-Paper-Conference.pdf"},{"key":"e_1_3_2_1_3_1","volume-title":"Joseph E. Gonzalez, Hao Zhang, and Ion Stoica.","author":"Kwon Woosuk","year":"2023","unstructured":"Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient Memory Management for Large Language Model Serving with PagedAttention. arXiv preprint arXiv:2309.06180 (2023). arXiv:2309.06180 [cs.OS] https:\/\/arxiv.org\/abs\/2309.06180"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Leviathan Yaniv","year":"2023","unstructured":"Yaniv Leviathan, Matan Kalman, and Yossi Matias. 2023. Fast inference from transformers via speculative decoding. In International Conference on Machine Learning. PMLR, 19274--19286."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3769102.3770608"},{"key":"e_1_3_2_1_6_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, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_7_1","volume-title":"Orca: A Distributed Serving System for Transformer-Based Generative Models. In 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). USENIX Association, Carlsbad, CA, 521--538. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658473"},{"key":"e_1_3_2_1_9_1","volume-title":"Edgeshard: Efficient llm inference via collaborative edge computing","author":"Zhang Mingjin","year":"2024","unstructured":"Mingjin Zhang, Xiaoming Shen, Jiannong Cao, Zeyang Cui, and Shan Jiang. 2024. Edgeshard: Efficient llm inference via collaborative edge computing. IEEE Internet of Things Journal (2024)."}],"event":{"name":"SIGMETRICS '26: ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","location":"Ann Arbor MI USA","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation"]},"container-title":["Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems"],"original-title":[],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T14:24:08Z","timestamp":1779805448000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801489.3806912"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,8]]},"references-count":9,"alternative-id":["10.1145\/3801489.3806912","10.1145\/3801489"],"URL":"https:\/\/doi.org\/10.1145\/3801489.3806912","relation":{},"subject":[],"published":{"date-parts":[[2026,6,8]]},"assertion":[{"value":"2026-06-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}