{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T11:58:28Z","timestamp":1792756708788,"version":"4.5.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11132861","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and Dataflow-flexible Accelerator"],"prefix":"10.1109","author":[{"given":"Zhican","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,State Key Laboratory of Micro\/Nano Engineering Science, School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxiang","family":"Fan","sequence":"additional","affiliation":[{"name":"Imperial College London,United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haroon","family":"Waris","sequence":"additional","affiliation":[{"name":"Institute of Space Technology,Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,State Key Laboratory of Micro\/Nano Engineering Science, School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,State Key Laboratory of Micro\/Nano Engineering Science, School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,State Key Laboratory of Micro\/Nano Engineering Science, School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanan","family":"Sun","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,State Key Laboratory of Micro\/Nano Engineering Science, School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanghui","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,State Key Laboratory of Micro\/Nano Engineering Science, School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","first-page":"114","article-title":"Keyformer: Kv cache reduction through key tokens selection for efficient generative inference","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Adnan"},{"key":"ref3","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin"},{"key":"ref5","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2414456"},{"key":"ref8","article-title":"Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Liu","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref10","article-title":"Online normalizer calculation for softmax","author":"Milakov","year":"2018","journal-title":"arXiv preprint arXiv:1805.02867"},{"key":"ref11","first-page":"28","article-title":"Cacti 6.0: A tool to model large caches","volume":"27","author":"Muralimanohar","year":"2009","journal-title":"HP laboratories"},{"key":"ref12","article-title":"Compressive transformers for long-range sequence modelling","author":"Rae","year":"2019","journal-title":"arXiv preprint arXiv:1911.05507"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401196"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref15","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247678"},{"key":"ref18","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023","journal-title":"arXiv preprint arXiv:2309.17453"},{"key":"ref19","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":"ref20","article-title":"Nn-lut: Neural approximation of non-linear operations for efficient transformer inference","author":"Yu","year":"2021"},{"key":"ref21","first-page":"34661","article-title":"H2o: Heavy-hitter oracle for efficient generative inference of large language models","volume":"36","author":"Zhang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11132861.pdf?arnumber=11132861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:24:33Z","timestamp":1758000273000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11132861","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}