{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T05:58:24Z","timestamp":1785563904103,"version":"3.56.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Research Foundation of Korea"},{"name":"Korean government","award":["RS-2024-00453929,RS-2024-00416666"],"award-info":[{"award-number":["RS-2024-00453929,RS-2024-00416666"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/ccgrid68966.2026.00014","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T18:13:59Z","timestamp":1785521639000},"page":"44-53","source":"Crossref","is-referenced-by-count":0,"title":["Quicktopia: Iteration-Level GPU Frequency Control for Energy\u2013Latency Co-Optimization in LLM Inference"],"prefix":"10.1109","author":[{"given":"Soyang","family":"Baek","sequence":"first","affiliation":[{"name":"Sogang University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bodon","family":"Jeong","sequence":"additional","affiliation":[{"name":"Sogang University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongsu","family":"Byun","sequence":"additional","affiliation":[{"name":"Sogang University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungyong","family":"Park","sequence":"additional","affiliation":[{"name":"Sogang University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Clone: customizing llms for efficient latency-aware inference at the edge","volume-title":"Proceedings of the 2025 USENIX Conference on Usenix Annual Technical Conference, USENIX ATC \u201925","author":"Tian"},{"key":"ref2","article-title":"Flexgen: high-throughput generative inference of large language models with a single gpu","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ICML\u201923, JMLR.org","author":"Sheng","year":"2023"},{"key":"ref3","first-page":"135","article-title":"ServerlessLLM: Low-Latency serverless inference for large language models","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Fu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"ref5","volume-title":"Greenllm: Slo-aware dynamic frequency scaling for energy-efficient llm serving","author":"Liu","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00103"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3307772.3328315"},{"key":"ref8","volume-title":"Investigating energy efficiency and performance trade-offs in llm inference across tasks and dvfs settings","author":"Maliakel","year":"2025"},{"key":"ref9","volume-title":"Atom: Low-bit quantization for efficient and accurate llm serving","author":"Zhao","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i38.40535"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SEC62691.2024.00023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2015.376"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref14","first-page":"521","article-title":"Orca: A distributed serving system for Transformer-Based generative models","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2198"},{"key":"ref16","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International conference on machine learning","author":"Xiao","year":"2023"},{"key":"ref17","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device 1lm compression and acceleration","volume-title":"Proceedings of machine learning and systems","volume":"6","author":"Lin","year":"2024"},{"key":"ref18","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"International Conference on Machine Learning","author":"Leviathan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP65064.2025.00031"},{"key":"ref20","article-title":"Camel: Energy-aware llm inference on resource-constrained devices","author":"Xu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1962.10490022"},{"issue":"3","key":"ref22","article-title":"Qwen2 technical report","volume":"2","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","volume-title":"share_gpt_small dataset.","author":"Larcher","year":"2024"},{"key":"ref25","volume-title":"Openchat: Advancing open-source language models with mixed-quality data","author":"Wang","year":"2024"}],"event":{"name":"2026 IEEE 26th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","location":"Sydney, Australia","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["2026 IEEE 26th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11618979\/11618983\/11619028.pdf?arnumber=11619028","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T05:13:46Z","timestamp":1785561226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11619028\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ccgrid68966.2026.00014","relation":{},"subject":[],"published":{"date-parts":[[2026,5]]}}}