{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T06:10:21Z","timestamp":1762409421062,"version":"build-2065373602"},"reference-count":9,"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.2025.3622724","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:39:39Z","timestamp":1760722779000},"page":"337-340","source":"Crossref","is-referenced-by-count":0,"title":["Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4718-8825","authenticated-orcid":false,"given":"Yunhua","family":"Fang","sequence":"first","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3177-5071","authenticated-orcid":false,"given":"Rui","family":"Xie","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7975-0102","authenticated-orcid":false,"given":"Asad Ul","family":"Haq","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8535-7911","authenticated-orcid":false,"given":"Linsen","family":"Ma","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1967-8749","authenticated-orcid":false,"given":"Kaoutar El","family":"Maghraoui","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7664-0061","authenticated-orcid":false,"given":"Naigang","family":"Wang","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0928-9691","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0792-8146","authenticated-orcid":false,"given":"Liu","family":"Liu","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8005-0043","authenticated-orcid":false,"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2024.3373763"},{"key":"ref3","first-page":"34661","article-title":"H2O: Heavy-hitter oracle for efficient generative inference of large language models","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref4","first-page":"47901","article-title":"QUEST: Query-aware sparsity for efficient long-context LLM inference","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Tang"},{"year":"2023","key":"ref5","article-title":"NVIDIA grace hopper superchip architecture"},{"key":"ref6","first-page":"117","article-title":"Taming throughput-latency tradeoff in LLM inference with Sarathi-Serve","volume-title":"Proc. 18th USENIX Symp. Operating Syst. Des. Implementation","author":"Agrawal"},{"year":"2024","key":"ref7","article-title":"Llama 3.1: A collection of multilingual large language models"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/science.220.4598.671"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/11062520\/11206428.pdf?arnumber=11206428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T05:56:24Z","timestamp":1762408584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11206428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":9,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lca.2025.3622724","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]]}}}