{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:24:59Z","timestamp":1776889499029,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018735","name":"Ant Group","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890367","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["DynamicAttention: Dynamic KV Cache for Disaggregate LLM Inference"],"prefix":"10.1109","author":[{"given":"Zhiqiang","family":"Ding","sequence":"first","affiliation":[{"name":"Ant Group,Platform Technology Business Unit,HangZhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongkai","family":"Yang","sequence":"additional","affiliation":[{"name":"Ant Group,Platform Technology Business Unit,HangZhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"31094","article-title":"Flexgen: High-throughput generative inference of large language models with a single gpu","volume-title":"International Conference on Machine Learning","author":"Sheng"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567508"},{"key":"ref3","author":"Hooper","year":"2024","journal-title":"Kvquant: Towards 10 million context length llm inference with kv cache quantization"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.195"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655823"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3625549.3658685"},{"key":"ref8","author":"Zhong","year":"2024","journal-title":"S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/jfpp.16772"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3732941"},{"key":"ref11","author":"Martinez","year":"2024","journal-title":"The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines"},{"key":"ref12","author":"Wang","year":"2024","journal-title":"LLM-assisted light: Leveraging large language model capabilities for human-mimetic traffic signal control in complex urban environments"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651335"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640423"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2008.4541126"},{"key":"ref16","author":"Zhong","year":"2024","journal-title":"Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref18","author":"Hu","year":"2024","journal-title":"MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS61025.2024.00037"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3606557.3606560"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00077"},{"key":"ref22","author":"Basile","year":"2023","journal-title":"LLaMAntino: LLaMA 2 models for effective text generation in Italian language"},{"key":"ref23","author":"Stojkovic","year":"2024","journal-title":"Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference"},{"key":"ref24","author":"Fu","year":"2024","journal-title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890367.pdf?arnumber=10890367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:45Z","timestamp":1774416225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890367","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}