{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:34:32Z","timestamp":1783035272875,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2315851"],"award-info":[{"award-number":["2315851"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2106634"],"award-info":[{"award-number":["2106634"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1145\/3769102.3770608","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T16:00:41Z","timestamp":1764777641000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5293-5348","authenticated-orcid":false,"given":"Xiangchen","family":"Li","sequence":"first","affiliation":[{"name":"Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0157-7173","authenticated-orcid":false,"given":"Dimitrios","family":"Spatharakis","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, 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":"School of Electronics, Electrical Engineering and Computer Science, Queen\u2019s University Belfast, Belfast, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4563-8697","authenticated-orcid":false,"given":"Jiakun","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5868-9259","authenticated-orcid":false,"given":"Hans","family":"Vandierendonck","sequence":"additional","affiliation":[{"name":"School of Electronics, Electrical Engineering and Computer Science, 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":"School of Electrical and Electronics Engineering, 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":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0217-8307","authenticated-orcid":false,"given":"Dimitrios S.","family":"Nikolopoulos","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Advances in Neural Information Processing Systems","author":"Brown Tom","year":"1877","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., Red Hook, NY, USA, 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"e_1_3_2_1_3_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_2_1_4_1","unstructured":"Tim Dettmers Mike Lewis Younes Belkada and Luke Zettlemoyer. 2022. LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale."},{"key":"e_1_3_2_1_5_1","volume-title":"March","year":"2025","unstructured":"eia2025electric 2025. Electric Power Monthly: Average Price of Electricity to Ultimate Customers by End-Use Sector, March 2025. https:\/\/www.eia.gov\/electricity\/monthly\/ accessed 17 Jun 2025."},{"key":"e_1_3_2_1_6_1","unstructured":"Mats Eriksson. 2020. Cost modelling of edge compute."},{"key":"e_1_3_2_1_7_1","unstructured":"Luyao Gao Jianchun Liu Hongli Xu Xichong Zhang Yunming Liao and Liusheng Huang. 2025. Collaborative Speculative Inference for Efficient LLM Inference Serving."},{"key":"e_1_3_2_1_8_1","volume-title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces.","author":"Gu Albert","year":"2024","unstructured":"Albert Gu and Tri Dao. 2024. Mamba: Linear-Time Sequence Modeling with Selective State Spaces."},{"key":"e_1_3_2_1_9_1","volume-title":"Dally","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William J. Dally. 2016. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding."},{"key":"e_1_3_2_1_10_1","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network."},{"key":"e_1_3_2_1_11_1","unstructured":"Kaiyu Huang Hao Wu Zhubo Shi Han Zou Minchen Yu and Qingjiang Shi. 2025. SpecServe: Efficient and SLO-Aware Large Language Model Serving with Adaptive Speculative Decoding."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.03360"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"SiYoung Jang and Roberto Morabito. 2025. Edge-First Language Model Inference: Models Metrics and Trade-offs. arXiv:2505.16508 Section IV defines PCR\/CPR cost metrics. 10.48550\/arXiv.2505.16508","DOI":"10.48550\/arXiv.2505.16508"},{"key":"e_1_3_2_1_14_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. https:\/\/arxiv.org\/abs\/2309.06180"},{"key":"e_1_3_2_1_15_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, Honolulu, Hawaii, USA, 19274\u201319286."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of Machine Learning and Systems, P. Gibbons, G. Pekhimenko, and C. De Sa (Eds.)","volume":"6","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration. In Proceedings of Machine Learning and Systems, P. Gibbons, G. Pekhimenko, and C. De Sa (Eds.), Vol. 6. MLSys, Santa Clara, CA, USA, 87\u2013100. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2024\/file\/42a452cbafa9dd64e9ba4aa95cc1ef21-Paper-Conference.pdf"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.39"},{"key":"e_1_3_2_1_18_1","unstructured":"Xiaoxuan Liu Cade Daniel Langxiang Hu Woosuk Kwon Zhuohan Li Xiangxi Mo Alvin Cheung Zhijie Deng Ion Stoica and Hao Zhang. 2024. Optimizing speculative decoding for serving large language models using goodput."},{"key":"e_1_3_2_1_19_1","unstructured":"Xinyin Ma Gongfan Fang and Xinchao Wang. 2023. LLM-Pruner: On the Structural Pruning of Large Language Models."},{"key":"e_1_3_2_1_20_1","volume-title":"Raspberry Pi 5 Review: A New Standard for Makers. https:\/\/www.tomshardware.com\/reviews\/raspberry-pi-5 Tom's Hardware, accessed","author":"O'Donnell Les","year":"2025","unstructured":"Les O'Donnell. 2023. Raspberry Pi 5 Review: A New Standard for Makers. https:\/\/www.tomshardware.com\/reviews\/raspberry-pi-5 Tom's Hardware, accessed 17 Jun 2025."},{"key":"e_1_3_2_1_21_1","volume-title":"Minjia Zhang, Ammar Ahmad Awan, Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, and Yuxiong He.","author":"Rajbhandari Samyam","year":"2022","unstructured":"Samyam Rajbhandari, Reza Yazdani Aminabadi, Minjia Zhang, Ammar Ahmad Awan, Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, and Yuxiong He. 2022. DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale. https:\/\/arxiv.org\/abs\/2207.00032"},{"key":"e_1_3_2_1_22_1","unstructured":"Mingjie Sun Zhuang Liu Anna Bair and J. Zico Kolter. 2024. A Simple and Effective Pruning Approach for Large Language Models."},{"key":"e_1_3_2_1_23_1","unstructured":"Zhiqing Sun Hongkun Yu Xiaodan Song Renjie Liu Yiming Yang and Denny Zhou. 2020. MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices."},{"key":"e_1_3_2_1_24_1","volume-title":"https:\/\/www.raspberrypi.com\/news\/introducing-raspberry-pi-5\/ Raspberry Pi Foundation blog, accessed","author":"Upton Eben","year":"2025","unstructured":"Eben Upton. 2023. Introducing Raspberry\u00a0Pi\u00a05. https:\/\/www.raspberrypi.com\/news\/introducing-raspberry-pi-5\/ Raspberry Pi Foundation blog, accessed 17 Jun 2025."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.127"},{"key":"e_1_3_2_1_26_1","unstructured":"Bingyang Wu Yinmin Zhong Zili Zhang Shengyu Liu Fangyue Liu Yuanhang Sun Gang Huang Xuanzhe Liu and Xin Jin. 2024. Fast Distributed Inference Serving for Large Language Models. https:\/\/arxiv.org\/abs\/2305.05920 arXiv:2305.05920."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3513457"},{"key":"e_1_3_2_1_28_1","volume-title":"Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference.","author":"Ye Shengyuan","year":"2024","unstructured":"Shengyuan Ye, Jiangsu Du, Liekang Zeng, Wenzhong Ou, Xiaowen Chu, Yutong Lu, and Xu Chen. 2024. Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference."},{"key":"e_1_3_2_1_29_1","volume-title":"Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices.","author":"Ye Shengyuan","year":"2025","unstructured":"Shengyuan Ye, Bei Ouyang, Liekang Zeng, Tianyi Qian, Xiaowen Chu, Jian Tang, and Xu Chen. 2025. Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices."},{"key":"e_1_3_2_1_30_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). OSDI, Carlsbad, CA, USA, 521\u2013538."},{"key":"e_1_3_2_1_31_1","volume-title":"Yang Katie Zhao, and Yingyan Celine Lin.","author":"Yu Zhongzhi","year":"2024","unstructured":"Zhongzhi Yu, Zheng Wang, Yuhan Li, Haoran You, Ruijie Gao, Xiaoya Zhou, Sreenidhi Reedy Bommu, Yang Katie Zhao, and Yingyan Celine Lin. 2024. EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Chao Zeng Songwei Liu Yusheng Xie Hong Liu Xiaojian Wang Miao Wei Shu Yang Fangmin Chen and Xing Mei. 2024. ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models.","DOI":"10.1609\/aaai.v39i21.34385"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"}],"event":{"name":"SEC '25: Tenth ACM\/IEEE Symposium on Edge Computing","location":"the Hilton Arlington National Landing Arlington VA USA","acronym":"SEC '25","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","IEEE Computer Society"]},"container-title":["Proceedings of the Tenth ACM\/IEEE Symposium on Edge Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3769102.3770608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T16:03:02Z","timestamp":1764777782000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769102.3770608"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":33,"alternative-id":["10.1145\/3769102.3770608","10.1145\/3769102"],"URL":"https:\/\/doi.org\/10.1145\/3769102.3770608","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]},"assertion":[{"value":"2025-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}