{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T07:40:03Z","timestamp":1751096403977,"version":"3.41.0"},"reference-count":17,"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"}],"funder":[{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003836","name":"IC Design Education Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003836","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,25]]},"DOI":"10.1109\/iscas56072.2025.11043714","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":0,"title":["A 4.21 TFLOPS\/W Memory-Efficient LLM Inference Accelerator with Bit-Layered Non-Uniform Quantization"],"prefix":"10.1109","author":[{"given":"Byeongcheol","family":"Kim","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangjin","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangwoo","family":"Ha","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soyeon","family":"Um","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyomin","family":"Sohn","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Memory Business Division,Hwaseong,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hoi-Jun","family":"Yoo","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3744746"},{"key":"ref2","article-title":"Samsung Galaxy S24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"article-title":"Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs","volume-title":"International Conference on Machin Learning (ICML)","author":"Hong","key":"ref4"},{"article-title":"SqueezeLLM: Dense-and-Sparse Quantization","volume-title":"International Conference on Machin Learning (ICML)","author":"Kim","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365943"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067615"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662302"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546846"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2024.3362699"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10558649"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3205713"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ESSCIRC55480.2022.9911343"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2006.876412"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00064"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"}],"event":{"name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2025,5,25]]},"location":"London, United Kingdom","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\/11043714.pdf?arnumber=11043714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T07:02:36Z","timestamp":1751094156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11043714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,25]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/iscas56072.2025.11043714","relation":{},"subject":[],"published":{"date-parts":[[2025,5,25]]}}}