{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T16:00:56Z","timestamp":1788451256166,"version":"build-2803163510"},"reference-count":18,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Korea Collaborative & High-tech Initiative for Prospective Semiconductor Research"},{"DOI":"10.13039\/501100004578","name":"Ministerstvo Pr\u016fmyslu a Obchodu","doi-asserted-by":"publisher","award":["RS-2025-02305531"],"award-info":[{"award-number":["RS-2025-02305531"]}],"id":[{"id":"10.13039\/501100004578","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Information Technology Research Center","award":["IITP-2025-2020-0-01461"],"award-info":[{"award-number":["IITP-2025-2020-0-01461"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/lca.2025.3567844","type":"journal-article","created":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T17:52:31Z","timestamp":1746640351000},"page":"165-168","source":"Crossref","is-referenced-by-count":4,"title":["OASIS: Outlier-Aware KV Cache Clustering for Scaling LLM Inference in CXL Memory Systems"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3648-5575","authenticated-orcid":false,"given":"Minseok","family":"Seo","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering (ECE), Inter-university Semiconductor Research Center, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7716-8886","authenticated-orcid":false,"given":"Jungi","family":"Hyun","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering (ECE), Inter-university Semiconductor Research Center, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4454-3800","authenticated-orcid":false,"given":"Seongho","family":"Jeong","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering (ECE), Inter-university Semiconductor Research Center, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7527-6971","authenticated-orcid":false,"given":"Xuan Truong","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering (ECE), Inter-university Semiconductor Research Center, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8895-9117","authenticated-orcid":false,"given":"Hyuk-Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering (ECE), Inter-university Semiconductor Research Center, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0824-6238","authenticated-orcid":false,"given":"Hyokeun","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of ECE, Ajou University, Suwon-si, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/567"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00077"},{"key":"ref3","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Sheng","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00027"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/PACT58117.2023.00016"},{"key":"ref6","first-page":"32332","article-title":"KIVI: A tuning-free asymmetric 2bit quantization for KV cache","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Liu","year":"2024"},{"key":"ref7","article-title":"GEAR: An efficient KV cache compression recipe for near-lossless generative inference of LLM","author":"Kang","year":"2024"},{"key":"ref8","article-title":"No token left behind: Reliable KV cache compression via importance-aware mixed precision quantization","author":"Yang","year":"2024"},{"key":"ref9","article-title":"DuoAttention: Efficient long-context LLM inference with retrieval and streaming heads","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiao","year":"2025"},{"key":"ref10","first-page":"22947","article-title":"SnapKV: LLM knows what you are looking for before generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651324"},{"key":"ref12","article-title":"LLaMA-2-7b-32k","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"ref14","article-title":"Cosine_similarity"},{"key":"ref15","article-title":"PQCache: Product quantization-based KVCache for long context LLM inference","author":"Zhang","year":"2025"},{"key":"ref16","article-title":"Efficient streaming language models with attention sinks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiao","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.195"},{"key":"ref18","article-title":"Llama-3-8b-instruct-gradient-1048k","year":"2024"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/10817484\/10990150.pdf?arnumber=10990150","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:37:15Z","timestamp":1750268235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10990150\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":18,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lca.2025.3567844","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":[[2025,1]]}}}