{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:23:12Z","timestamp":1757622192960,"version":"3.44.0"},"reference-count":16,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":[[2025,7]]},"DOI":"10.1109\/lca.2025.3597323","type":"journal-article","created":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T17:42:32Z","timestamp":1754934152000},"page":"285-288","source":"Crossref","is-referenced-by-count":0,"title":["AiDE: Attention-FFN Disaggregated Execution for Cost-Effective LLM Decoding on CXL-PNM"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8927-1530","authenticated-orcid":false,"given":"KyungSoo","family":"Kim","sequence":"first","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7468-0810","authenticated-orcid":false,"given":"Omin","family":"Kwon","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeonhong","family":"Park","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4266-4919","authenticated-orcid":false,"given":"Jae W.","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/isca59077.2024.00019"},{"year":"2025","key":"ref2","article-title":"NVIDIA dynamo"},{"year":"2024","key":"ref3","article-title":"DeepSeek-V3\/R1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/hpca57654.2024.00078"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716267"},{"key":"ref9","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lewis","year":"2020"},{"key":"ref10","first-page":"111","article-title":"Cost-efficient large language model serving for multi-turn conversations with CachedAttention","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Gao","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"article-title":"Fast transformer decoding: One write-head is all you need","year":"2019","author":"Shazeer","key":"ref13"},{"article-title":"Longformer: The long-document transformer","year":"2020","author":"Beltagy","key":"ref14"},{"key":"ref15","first-page":"52481","article-title":"MInference 1.0: Accelerating pre-filling for long-context LLMs via dynamic sparse attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang","year":"2024"},{"year":"2023","key":"ref16","article-title":"vLLM: Easy, fast, and cheap LLM serving"},{"year":"2023","key":"ref17","article-title":"LLaMA"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/11062520\/11122346.pdf?arnumber=11122346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:43:16Z","timestamp":1757353396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11122346\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":16,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lca.2025.3597323","relation":{},"ISSN":["1556-6056","1556-6064","2473-2575"],"issn-type":[{"type":"print","value":"1556-6056"},{"type":"electronic","value":"1556-6064"},{"type":"electronic","value":"2473-2575"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}