{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T08:53:21Z","timestamp":1793436801585,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":7,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T00:00:00Z","timestamp":1781913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union's Horizon Europe Framework Programme","award":["101135775"],"award-info":[{"award-number":["101135775"]}]},{"name":"NordForsk","award":["168043"],"award-info":[{"award-number":["168043"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,21]]},"DOI":"10.1145\/3812836.3814999","type":"proceedings-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:54:53Z","timestamp":1780419293000},"page":"51-56","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Profiling-Driven Adaptive Distributed Transformer Inference on Embedded Edge Deployment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4253-8701","authenticated-orcid":false,"given":"Muhammad Azlan","family":"Qazi","sequence":"first","affiliation":[{"name":"Aarhus University, Aarhus, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4807-1345","authenticated-orcid":false,"given":"Alexandros","family":"Iosifidis","sequence":"additional","affiliation":[{"name":"Tampere University, Tampere, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5303-9804","authenticated-orcid":false,"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Aarhus University, Aarhus, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Weinberger (Eds.)","volume":"25","author":"Dean Jeffrey","year":"2012","unstructured":"Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Marc' aurelio Ranzato, Andrew Senior, Paul Tucker, Ke Yang, Quoc Le, and Andrew Ng. 2012. Large Scale Distributed Deep Networks. In Advances in Neural Information Processing Systems, F. Pereira, C.J. Burges, L. Bottou, and K.Q. Weinberger (Eds.), Vol. 25. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2012\/file\/6aca97005c68f1206823815f66102863-Paper.pdf"},{"key":"e_1_3_2_1_2_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv:2010.11929 [cs.CV] https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00017"},{"key":"e_1_3_2_1_4_1","volume-title":"Dehao Chen, Hyouk Joong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen.","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Mia Xu Chen, Dehao Chen, Hyouk Joong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. 2019. GPipe: efficient training of giant neural networks using pipeline parallelism. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_5_1","volume-title":"Gloo: Collective Communications Library. https:\/\/github.com\/pytorch\/gloo","author":"Contributors PyTorch","year":"2026","unstructured":"PyTorch Contributors. 2026. Gloo: Collective Communications Library. https:\/\/github.com\/pytorch\/gloo"},{"key":"e_1_3_2_1_6_1","volume-title":"PRISM: Distributed Inference for Foundation Models at Edge. arXiv preprint arXiv:2507.12145","author":"Qazi Muhammad Azlan","year":"2025","unstructured":"Muhammad Azlan Qazi, Alexandros Iosifidis, and Qi Zhang. 2025. PRISM: Distributed Inference for Foundation Models at Edge. arXiv preprint arXiv:2507.12145 (2025)."},{"key":"e_1_3_2_1_7_1","volume-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. ArXiv abs\/1909.08053","author":"Shoeybi Mohammad","year":"2019","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. ArXiv abs\/1909.08053 (2019). https:\/\/api.semanticscholar.org\/CorpusID:202660670"}],"event":{"name":"MobiSys Workshop '26: 24th Annual International Conference on Mobile Systems, Applications and Services Workshops","location":"University of Cambridge Cambridge United Kingdom","acronym":"MobiSys Workshop '26","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 24th Annual International Conference on Mobile Systems, Applications and Services Workshops"],"original-title":[],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:55:05Z","timestamp":1780419305000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3812836.3814999"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,20]]},"references-count":7,"alternative-id":["10.1145\/3812836.3814999","10.1145\/3812836"],"URL":"https:\/\/doi.org\/10.1145\/3812836.3814999","relation":{},"subject":[],"published":{"date-parts":[[2026,6,20]]},"assertion":[{"value":"2026-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}