{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:34:07Z","timestamp":1781886847818,"version":"3.54.5"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T00:00:00Z","timestamp":1748131200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T00:00:00Z","timestamp":1748131200000},"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":[[2025,5,25]]},"DOI":"10.1109\/iscas56072.2025.11043957","type":"proceedings-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T17:42:19Z","timestamp":1751046139000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Optimizing Sparse\/Dense VEGETA Accelerator Performance with Microscaling Quantization"],"prefix":"10.1109","author":[{"given":"Kazi Barria","family":"Nine","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Connor","family":"Talley","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajay Sharma","family":"Mandadi","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tushar","family":"Krishna","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arijit","family":"Raychowdhury","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.teler.2024.100116"},{"issue":"5","key":"ref2","first-page":"1234","article-title":"A survey on model compression for large language models","volume":"24","author":"Zhu","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","article-title":"Learning recurrent binary\/ternary weights","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Ardakani"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5038-2_4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3197608"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-0425-6_7"},{"key":"ref8","first-page":"27168","article-title":"Zeroquant: Efficient and affordable post-training quantization for large-scale transformers","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"10271","article-title":"Pushing the limits of narrow precision inferencing at cloud scale with microsoft floating point","volume":"33","author":"Darvish Rouhani","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"873","article-title":"Vs-quant: Per-vector scaled quantization for accurate low-precision neural network inference","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"Dai"},{"key":"ref11","article-title":"Microscaling data formats for deep learning","author":"Rouhani","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071058"},{"key":"ref14","article-title":"Scalesim: Systolic cnn accelerator simulator","author":"Samajdar","year":"2019"}],"event":{"name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"London, United Kingdom","start":{"date-parts":[[2025,5,25]]},"end":{"date-parts":[[2025,5,28]]}},"container-title":["2025 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11043142\/11042930\/11043957.pdf?arnumber=11043957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T06:46:50Z","timestamp":1751093210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11043957\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,25]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/iscas56072.2025.11043957","relation":{},"subject":[],"published":{"date-parts":[[2025,5,25]]}}}