{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T13:24:57Z","timestamp":1773840297982,"version":"3.50.1"},"reference-count":10,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/lca.2024.3452699","type":"journal-article","created":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T17:35:13Z","timestamp":1725298513000},"page":"199-202","source":"Crossref","is-referenced-by-count":2,"title":["SmartQuant: CXL-Based AI Model Store in Support of Runtime Configurable Weight Quantization"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3177-5071","authenticated-orcid":false,"given":"Rui","family":"Xie","sequence":"first","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"given":"Asad Ul","family":"Haq","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"given":"Linsen","family":"Ma","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"given":"Krystal","family":"Sun","sequence":"additional","affiliation":[{"name":"BASIS Independent Fremont, Fremont, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0080-2882","authenticated-orcid":false,"given":"Sanchari","family":"Sen","sequence":"additional","affiliation":[{"name":"IBM, Armonk, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0470-6364","authenticated-orcid":false,"given":"Swagath","family":"Venkataramani","sequence":"additional","affiliation":[{"name":"IBM, Armonk, NY, USA"}]},{"given":"Liu","family":"Liu","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0985-7986","authenticated-orcid":false,"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref4","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref5","first-page":"22 137","article-title":"Deja Vu: Contextual sparsity for efficient LLMs at inference time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3669900"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2973991"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2862938"},{"issue":"140","key":"ref9","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/10700665\/10663202.pdf?arnumber=10663202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T01:02:07Z","timestamp":1732669327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10663202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":10,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lca.2024.3452699","relation":{},"ISSN":["1556-6056","1556-6064","2473-2575"],"issn-type":[{"value":"1556-6056","type":"print"},{"value":"1556-6064","type":"electronic"},{"value":"2473-2575","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}