{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T18:55:25Z","timestamp":1760986525122,"version":"build-2065373602"},"reference-count":13,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0660101","XDB0660000","XDB0660100"],"award-info":[{"award-number":["XDB0660101","XDB0660000","XDB0660100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172380"],"award-info":[{"award-number":["62172380"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241818"],"award-info":[{"award-number":["BK20241818"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["Y2021121"],"award-info":[{"award-number":["Y2021121"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"name":"USTC Research Funds of the Double First-Class Initiative","award":["YD2150002011"],"award-info":[{"award-number":["YD2150002011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Embedded Syst. Lett."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/les.2025.3600563","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:37:45Z","timestamp":1760636265000},"page":"337-340","source":"Crossref","is-referenced-by-count":0,"title":["QLlama: An FPGA-Based Microscaling Quantization Accelerator for Energy-Efficient Llama2 Inference"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5845-392X","authenticated-orcid":false,"given":"Hongbing","family":"Wen","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiale","family":"Dong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2240-6672","authenticated-orcid":false,"given":"Wenqi","family":"Lou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8391-5526","authenticated-orcid":false,"given":"Lei","family":"Gong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9403-5575","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-3143","authenticated-orcid":false,"given":"Xuehai","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3649476.3658810"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3110413"},{"key":"ref4","first-page":"1","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","volume-title":"Proc. ICLR","author":"Frantar"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29237"},{"key":"ref6","article-title":"Microscaling data formats for deep learning","author":"Rouhani","year":"2023","journal-title":"arXiv:2310.10537"},{"key":"ref7","first-page":"1","article-title":"HLSTransform: Energy-efficient Llama 2 inference on FPGAs via high level synthesis","volume-title":"Proc. Workshop ICML","author":"He"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref11","first-page":"1","article-title":"Root mean square layer normalization","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"}],"container-title":["IEEE Embedded Systems Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4563995\/11205899\/11205910.pdf?arnumber=11205910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:49:55Z","timestamp":1760982595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11205910\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":13,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/les.2025.3600563","relation":{},"ISSN":["1943-0663","1943-0671"],"issn-type":[{"type":"print","value":"1943-0663"},{"type":"electronic","value":"1943-0671"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}