{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:38:21Z","timestamp":1776357501124,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2027,4,26]],"date-time":"2027-04-26T00:00:00Z","timestamp":1808697600000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100016337","name":"Department for the Economy, Northern Ireland","doi-asserted-by":"publisher","award":["USI-226"],"award-info":[{"award-number":["USI-226"]}],"id":[{"id":"10.13039\/100016337","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016337","name":"Virginia Tech College of Engineering","doi-asserted-by":"publisher","award":["Major Grants Initiative Program"],"award-info":[{"award-number":["Major Grants Initiative Program"]}],"id":[{"id":"10.13039\/100016337","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"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"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3802513.3803483","type":"proceedings-article","created":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T19:14:33Z","timestamp":1776194073000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ConfigSpec: Profiling-Based Configuration Selection for Distributed Edge-Cloud Speculative LLM Serving"],"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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0542-848X","authenticated-orcid":false,"given":"Babar","family":"Ali","sequence":"additional","affiliation":[{"name":"Queen's University Belfast, Belfast, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5868-9259","authenticated-orcid":false,"given":"Hans","family":"Vandierendonck","sequence":"additional","affiliation":[{"name":"Queen's University Belfast, Belfast, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0217-8307","authenticated-orcid":false,"given":"Dimitrios S.","family":"Nikolopoulos","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318","author":"Chen Charlie","year":"2023","unstructured":"Charlie Chen, Sebastian Borgeaud, Geoffrey Irving, Jean-Baptiste Lespiau, Laurent Sifre, and John Jumper. 2023. Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.498"},{"key":"e_1_3_2_1_3_1","volume-title":"Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM. https:\/\/www.databricks.com\/blog\/2023\/04\/12\/dolly-first-open-commercially-viable-instruction-tuned-llm","author":"Conover Mike","year":"2023","unstructured":"Mike Conover, Matt Hayes, Ankit Mathur, Jianwei Xie, Jun Wan, Sam Shah, Ali Ghodsi, Patrick Wendell, Matei Zaharia, and Reynold Xin. 2023. Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM. https:\/\/www.databricks.com\/blog\/2023\/04\/12\/dolly-first-open-commercially-viable-instruction-tuned-llm"},{"key":"e_1_3_2_1_4_1","unstructured":"Fireworks AI. 2025. Pricing - Fireworks AI. https:\/\/fireworks.ai\/pricing. Serverless tier: $0.90 \/ 1M tokens for models >16B parameters. Accessed: 2025-07-15."},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Machine Learning. PMLR, 10323\u201310337","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar and Dan Alistarh. 2023. Sparsegpt: Massive language models can be accurately pruned in one-shot. In International Conference on Machine Learning. PMLR, 10323\u201310337."},{"key":"e_1_3_2_1_6_1","unstructured":"Groq. 2025. GroqCloud On-Demand Pricing. https:\/\/groq.com\/pricing. Qwen3-32B: $0.29 \/ 1M input tokens $0.59 \/ 1M output tokens. Accessed: 2025-07-15."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3583764"},{"key":"e_1_3_2_1_8_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_9_1","volume-title":"Adaptive model partitioning and pruning for collaborative DNN inference in mobile edge-cloud computing networks","author":"Li Hui","year":"2025","unstructured":"Hui Li, Xiuhua Li, Qilin Fan, Qiang He, Xiaofei Wang, and Victor CM Leung. 2025. Adaptive model partitioning and pruning for collaborative DNN inference in mobile edge-cloud computing networks. IEEE Transactions on Mobile Computing (2025)."},{"key":"e_1_3_2_1_10_1","volume-title":"WISP: Waste-and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching. arXiv preprint arXiv:2601.11652","author":"Li Xiangchen","year":"2026","unstructured":"Xiangchen Li, Jiakun Fan, Qingyuan Wang, Dimitrios Spatharakis, Saeid Ghafouri, Hans Vandierendonck, Deepu John, Bo Ji, Ali R Butt, and Dimitrios S Nikolopoulos. 2026. WISP: Waste-and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching. arXiv preprint arXiv:2601.11652 (2026)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3769102.3770608"},{"key":"e_1_3_2_1_12_1","volume-title":"Zhuoming Chen, Daiyaan Arfeen, Reyna Abhyankar, and Zhihao Jia.","author":"Miao Xupeng","year":"2023","unstructured":"Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Zeyu Wang, Rae Ying Yee Wong, Zhuoming Chen, Daiyaan Arfeen, Reyna Abhyankar, and Zhihao Jia. 2023. Specinfer: Accelerating generative llm serving with speculative inference and token tree verification. arXiv preprint arXiv:2305.09781 1, 2 (2023), 4."},{"key":"e_1_3_2_1_13_1","volume-title":"MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding. In International Conference on Learning Representations.","author":"Sadhukhan Ranajoy","year":"2024","unstructured":"Ranajoy Sadhukhan, Jian Chen, Zhuoming Chen, Vashisth Tiwari, Ruihang Lai, Jinyuan Shi, Ian En-Hsu Yen, Avner May, Tianqi Chen, and Beidi Chen. 2024. MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 2025 USENIX Conference on Usenix Annual Technical Conference (Boston, MA, USA) (USENIX ATC '25). USENIX Association, USA, Article 34","author":"Tian Chunlin","year":"2025","unstructured":"Chunlin Tian, Xinpeng Qin, Kahou Tam, Li Li, Zijian Wang, Yuanzhe Zhao, Minglei Zhang, and Chengzhong Xu. 2025. CLONE: customizing LLMs for efficient latency-aware inference at the edge. In Proceedings of the 2025 USENIX Conference on Usenix Annual Technical Conference (Boston, MA, USA) (USENIX ATC '25). USENIX Association, USA, Article 34, 23 pages."},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Machine Learning. PMLR, 38087\u201338099","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2023. Smoothquant: Accurate and efficient post-training quantization for large language models. In International Conference on Machine Learning. PMLR, 38087\u201338099."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3513457"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658473"},{"key":"e_1_3_2_1_18_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":"TDIS '26: 21st European Conference on Computer Systems","location":"Edinburgh Scotland Uk","acronym":"TDIS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 4th International Workshop on Testing Distributed Internet of Things Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3802513.3803483","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T15:33:27Z","timestamp":1776353607000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3802513.3803483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":18,"alternative-id":["10.1145\/3802513.3803483","10.1145\/3802513"],"URL":"https:\/\/doi.org\/10.1145\/3802513.3803483","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}