{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T16:08:02Z","timestamp":1764778082160,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1145\/3769102.3774241","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T16:00:41Z","timestamp":1764777641000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["How Heavy is the Edge? Resource Utilization of Edge Generative AI on Distributed AI Infrastructure"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1546-8144","authenticated-orcid":false,"given":"Liang","family":"Wu","sequence":"first","affiliation":[{"name":"University of Wisconsin-Milwaukee, Milwaukee, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7877-292X","authenticated-orcid":false,"given":"Zhen","family":"Zeng","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Milwaukee, Milwaukee, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9624-2669","authenticated-orcid":false,"given":"Zhongshu","family":"Gu","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0826-1614","authenticated-orcid":false,"given":"Pengxia","family":"Wu","sequence":"additional","affiliation":[{"name":"Rockwell Automation, Milwaukee, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2025. Kubernetes Documentation. https:\/\/kubernetes.io\/docs\/. Accessed: 2025-05-04."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Meta AI. 2024. Llama-3.2-1B. https:\/\/huggingface.co\/meta-llama\/Llama-3.2-1B. Accessed: 2025-05-04.","DOI":"10.55041\/ISJEM03638"},{"key":"e_1_3_2_1_3_1","unstructured":"Sandeep Akkamath et al. 2024. Unlocking Full Prefill-Decode Overlap for Faster LLM Inference. arXiv preprint arXiv:2410.18038 (2024)."},{"key":"e_1_3_2_1_4_1","volume-title":"Ray: The AI Compute Engine. https:\/\/www.anyscale.com\/product\/open-source\/ray. Accessed: 2025-05-02.","author":"Anyscale Inc.","year":"2025","unstructured":"Anyscale Inc. 2025. Ray: The AI Compute Engine. https:\/\/www.anyscale.com\/product\/open-source\/ray. Accessed: 2025-05-02."},{"key":"e_1_3_2_1_5_1","volume-title":"Democratizing Edge Intelligence with Network-Edge AI\/ML Orchestration: The NAOMI Framework. In 2023 IEEE Conference on Standards for Communications and Networking (CSCN). IEEE","author":"Donno Michele","year":"2023","unstructured":"Michele Donno, Konstantinos Karras, Hans D. Schotten, Slawomir Kuklinski, and Guenter Klas. 2023. Democratizing Edge Intelligence with Network-Edge AI\/ML Orchestration: The NAOMI Framework. In 2023 IEEE Conference on Standards for Communications and Networking (CSCN). IEEE, Thessaloniki, Greece, 1\u20136."},{"key":"e_1_3_2_1_6_1","volume-title":"TinyLLM: A Framework for Training and Deploying Language Models at the Edge Computers. arXiv preprint arXiv:2412.15304 (Dec","author":"Kandala Savitha Viswanadh","year":"2024","unstructured":"Savitha Viswanadh Kandala, Pramuka Medaranga, and Ambuj Varshney. 2024. TinyLLM: A Framework for Training and Deploying Language Models at the Edge Computers. arXiv preprint arXiv:2412.15304 (Dec 2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the ICML 2024 Workshop on Efficient Systems for Foundation Models (ES-FoMo)","author":"Laskaridis Saksham","year":"2024","unstructured":"Saksham Laskaridis, Konstantinos Katevas, Luke Minto, and Hamed Haddadi. 2024. Mobile and Edge Evaluation of Large Language Models. In Proceedings of the ICML 2024 Workshop on Efficient Systems for Foundation Models (ES-FoMo). Vienna, Austria."},{"key":"e_1_3_2_1_8_1","volume-title":"Ray: A Distributed Framework for Emerging AI Applications. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I Jordan, and Ion Stoica. 2018. Ray: A Distributed Framework for Emerging AI Applications. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). USENIX Association, Carlsbad, CA, 561\u2013577."},{"key":"e_1_3_2_1_9_1","unstructured":"O-RAN Alliance. 2021. O-RAN Working Group 2 AI\/ML Workflow Description and Requirements. Technical Report. ORAN-WG2.AIML.v01.03."},{"key":"e_1_3_2_1_10_1","unstructured":"OpenAI. 2019. GPT-2. https:\/\/huggingface.co\/openai-community\/gpt2. Accessed: 2025-05-04."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of Machine Learning and Systems","volume":"5","author":"Pope R.","unstructured":"R. Pope, S. Douglas, A. Chowdhery, J. Devlin, J. Bradbury, J. Heek, K. Xiao, S. Agrawal, and J. Dean. 2023. Efficiently scaling transformer inference. In Proceedings of Machine Learning and Systems, Vol. 5."},{"key":"e_1_3_2_1_12_1","volume-title":"Large Language Models On-Device with MediaPipe and TensorFlow Lite. https:\/\/developers.googleblog.com\/2024\/03\/running-large-language-models-on-device-with-mediapipe-andtensorflow-lite.html","author":"Sherwood Mark","year":"2024","unstructured":"Mark Sherwood. 2024. Large Language Models On-Device with MediaPipe and TensorFlow Lite. https:\/\/developers.googleblog.com\/2024\/03\/running-large-language-models-on-device-with-mediapipe-andtensorflow-lite.html. Accessed: March 2024."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.02.004"},{"key":"e_1_3_2_1_14_1","unstructured":"TinyLlama. 2023. TinyLlama-1.1B-Chat-v1.0. https:\/\/huggingface.co\/TinyLlama\/TinyLlama-1.1B-Chat-v1.0. Accessed: 2025-05-04."}],"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\/3769102.3774241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T16:03:35Z","timestamp":1764777815000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769102.3774241"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":14,"alternative-id":["10.1145\/3769102.3774241","10.1145\/3769102"],"URL":"https:\/\/doi.org\/10.1145\/3769102.3774241","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"}}]}}