{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T22:24:30Z","timestamp":1793658270565,"version":"4.5.1"},"reference-count":15,"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.2024.3406038","type":"journal-article","created":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T13:46:26Z","timestamp":1716903986000},"page":"150-153","source":"Crossref","is-referenced-by-count":46,"title":["SLO-Aware GPU DVFS for Energy-Efficient LLM Inference Serving"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4915-8309","authenticated-orcid":false,"given":"Andreas Kosmas","family":"Kakolyris","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering (ECE), National Technical University of Athens, Zografou, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6147-6908","authenticated-orcid":false,"given":"Dimosthenis","family":"Masouros","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering (ECE), National Technical University of Athens, Zografou, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3151-2730","authenticated-orcid":false,"given":"Sotirios","family":"Xydis","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering (ECE), National Technical University of Athens, Zografou, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6930-6847","authenticated-orcid":false,"given":"Dimitrios","family":"Soudris","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering (ECE), National Technical University of Athens, Zografou, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref2","article-title":"Exclusive: ChatGPT traffic slips again for third month in a row","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00033"},{"key":"ref4","first-page":"1241","article-title":"Thunderbolt: Throughput-optimized quality-of-service-aware power capping at scale","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Li"},{"key":"ref5","article-title":"POLCA: Power oversubscription in LLM cloud providers","author":"Patel","year":"2023"},{"key":"ref6","first-page":"473","article-title":"Prediction-based power oversubscription in cloud platforms","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Kumbhare"},{"key":"ref7","first-page":"1049","article-title":"MArk: Exploiting cloud services for cost-effective, SLO-aware machine learning inference serving","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Zhang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363447"},{"key":"ref9","first-page":"521","article-title":"Orca: A distributed serving system for transformer-based generative models","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Des. Implementation","author":"Yu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3638757"},{"key":"ref11","first-page":"613","article-title":"Clipper: A Low-latency online prediction serving system","volume-title":"Proc. 14th USENIX Symp. Netw. Syst. Des. Implementation","author":"Crankshaw"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3144614"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607034"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref15","first-page":"945","article-title":"MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters","volume-title":"Proc. 19th USENIX Symp. Netw. Syst. Des. Implementation","author":"Weng"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10208\/10700665\/10540202.pdf?arnumber=10540202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T13:25:21Z","timestamp":1727789121000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10540202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":15,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lca.2024.3406038","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]]}}}