{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T06:10:34Z","timestamp":1778566234854,"version":"3.51.4"},"reference-count":21,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61934002"],"award-info":[{"award-number":["61934002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62234008"],"award-info":[{"award-number":["62234008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. VLSI Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tvlsi.2026.3659893","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:03:40Z","timestamp":1770930220000},"page":"1393-1397","source":"Crossref","is-referenced-by-count":0,"title":["Area- and Utilization-Efficient LLM Accelerator With Fused Speculative Decoding for Edge-Side Inference"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6439-3255","authenticated-orcid":false,"given":"Kaiqi","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2530-3886","authenticated-orcid":false,"given":"Zikang","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaqi","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5245-0754","authenticated-orcid":false,"given":"Jun","family":"Han","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/info16080688"},{"key":"ref2","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref3","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref4","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.456"},{"key":"ref7","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Leviathan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651335"},{"key":"ref9","first-page":"39236","article-title":"Speculative decoding with big little decoder","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref10","first-page":"11263","article-title":"Draft & verify: Lossless large language model acceleration via self-speculative decoding","volume-title":"Proc. 62nd Annu. Meeting Assoc. Comput. Linguistics","author":"Zhang"},{"key":"ref11","article-title":"Predictive pipelined decoding: A compute-latency trade-off for exact LLM decoding","author":"Yang","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-85747-8_2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref14","first-page":"1693","article-title":"Teaching machines to read and comprehend","volume-title":"Proc. 29th Int. Conf. Neural Inf. Process. Syst.","author":"Hermann"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1206"},{"key":"ref16","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv:1609.07843"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228584"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2025.3546256"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2024.3409640"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3307607"}],"container-title":["IEEE Transactions on Very Large Scale Integration (VLSI) Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/92\/11514136\/11394827.pdf?arnumber=11394827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T05:16:54Z","timestamp":1778563014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11394827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":21,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tvlsi.2026.3659893","relation":{},"ISSN":["1063-8210","1557-9999"],"issn-type":[{"value":"1063-8210","type":"print"},{"value":"1557-9999","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}