{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T20:06:35Z","timestamp":1779739595612,"version":"3.53.1"},"reference-count":11,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["112-2221-E-002-116-MY3"],"award-info":[{"award-number":["112-2221-E-002-116-MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Macronix Inc., Hsin-chu, Taiwan","award":["115HT912003"],"award-info":[{"award-number":["115HT912003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/lca.2026.3679296","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:52:01Z","timestamp":1774986721000},"page":"178-181","source":"Crossref","is-referenced-by-count":0,"title":["Efficient MoE Model Fine-Tuning on Commodity GPU Server With Offloading"],"prefix":"10.1109","volume":"25","author":[{"given":"Yu-Hu","family":"Kuo","sequence":"first","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3339-9959","authenticated-orcid":false,"given":"Hung-Tso","family":"Shiao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0091-5027","authenticated-orcid":false,"given":"Chia-Lin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Efficient large-scale language model training on GPU clusters using Megatron-LM","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Narayanan","year":"2021"},{"key":"ref2","first-page":"1","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lepikhin","year":"2021"},{"key":"ref3","article-title":"Training large neural networks with constant memory using a new execution algorithm","author":"Pudipeddi","year":"2020","journal-title":"arXiv: 2002.05645"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508418"},{"key":"ref5","first-page":"18332","article-title":"Deepspeed-moe: Advancing mixture-of-experts inference and training to power next-generation AI scale","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Rajbhandari","year":"2022"},{"key":"ref6","article-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"key":"ref7","first-page":"961","article-title":"SmartMoE: Efficiently training sparsely-activated models through combining offline and online parallelization","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Zhai","year":"2023"},{"key":"ref8","first-page":"22137","article-title":"Deja vu: Contextual sparsity for efficient llms at inference time","volume-title":"Proc. 2023 Int. Conf. Mach. Learn.","author":"Liu","year":"2023"},{"key":"ref9","article-title":"Upcycling large language models into mixture of experts","author":"He","year":"2024"},{"key":"ref10","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref11","article-title":"Stanford alpaca: An instruction-following LLAMA model","author":"Taori","year":"2023"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/11321093\/11458790.pdf?arnumber=11458790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T19:52:54Z","timestamp":1779738774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11458790\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":11,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lca.2026.3679296","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":[[2026,1]]}}}