{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T06:44:24Z","timestamp":1775630664702,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1109\/icmla66185.2025.00119","type":"proceedings-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:54:58Z","timestamp":1775591698000},"page":"814-819","source":"Crossref","is-referenced-by-count":0,"title":["EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model"],"prefix":"10.1109","author":[{"given":"Alyssa","family":"Pinnock","sequence":"first","affiliation":[{"name":"University of Central Florida"}]},{"given":"Shakya","family":"Jayakody","sequence":"additional","affiliation":[{"name":"University of Central Florida"}]},{"given":"Kawsher A","family":"Roxy","sequence":"additional","affiliation":[{"name":"Intel Corporation"}]},{"given":"Md Rubel","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Louisiana Tech University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CAI59869.2024.00159"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/s23031279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2198"},{"key":"ref4","article-title":"Llama guard: Llm-based input-output safeguard for human-ai conversations","author":"Inan","year":"2023"},{"key":"ref5","article-title":"On-device llms for smes: Challenges and opportunities","author":"Yee","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref8","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021"},{"key":"ref9","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume":"32","author":"Banner","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1970"},{"key":"ref11","article-title":"Learned step size quantization","author":"Esser","year":"2019"},{"key":"ref12","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3736721"},{"key":"ref14","article-title":"Mobilellm: Optimizing sub-billion parameter language models for on-device use cases","volume-title":"Forty-first International Conference on Machine Learning","author":"Liu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.348"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.678"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-85747-8_3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3736721"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3443718"},{"key":"ref20","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device llm compression and acceleration","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Lin"},{"key":"ref21","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao"}],"event":{"name":"2025 International Conference on Machine Learning and Applications (ICMLA)","location":"Boca Raton, FL, USA","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 International Conference on Machine Learning and Applications (ICMLA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11471302\/11471304\/11471314.pdf?arnumber=11471314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:44:46Z","timestamp":1775627086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11471314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icmla66185.2025.00119","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}