{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T19:49:04Z","timestamp":1769024944371,"version":"3.49.0"},"reference-count":7,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T00:00:00Z","timestamp":1723334400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T00:00:00Z","timestamp":1723334400000},"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":[[2024,8,11]]},"DOI":"10.1109\/mwscas60917.2024.10658754","type":"proceedings-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T17:34:29Z","timestamp":1726508069000},"page":"253-257","source":"Crossref","is-referenced-by-count":3,"title":["Co-design of a TinyLLM using Programmable Logic and Software on an FPGA"],"prefix":"10.1109","author":[{"given":"Michael","family":"Muller","sequence":"first","affiliation":[{"name":"Oakland University,Rochester,MI,USA"}]},{"given":"Alexander","family":"Tyshka","sequence":"additional","affiliation":[{"name":"Oakland University,Rochester,MI,USA"}]},{"given":"Max","family":"Theisen","sequence":"additional","affiliation":[{"name":"Oakland University,Rochester,MI,USA"}]},{"given":"Darrin","family":"Hanna","sequence":"additional","affiliation":[{"name":"Oakland University,Rochester,MI,USA"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"The obscene energy demands of A.I.","author":"Kolbert","year":"2024"},{"key":"ref2","first-page":"31094","article-title":"Flexgen: High-throughput generative inference of large language models with a single gpu","volume-title":"International Conference on Machine Learning.","author":"Sheng"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637600"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2023.3302182"},{"key":"ref6","article-title":"Tinystories: How small can language models be and still speak coherent english?","author":"Eldan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","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":"2024 IEEE 67th International Midwest Symposium on Circuits and Systems (MWSCAS)","location":"Springfield, MA, USA","start":{"date-parts":[[2024,8,11]]},"end":{"date-parts":[[2024,8,14]]}},"container-title":["2024 IEEE 67th International Midwest Symposium on Circuits and Systems (MWSCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10654782\/10654792\/10658754.pdf?arnumber=10658754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T06:11:39Z","timestamp":1726812699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10658754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,11]]},"references-count":7,"URL":"https:\/\/doi.org\/10.1109\/mwscas60917.2024.10658754","relation":{},"subject":[],"published":{"date-parts":[[2024,8,11]]}}}