"VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and ..."

Zhican Wang et al. (2025)

> Home

Details and statistics

DOI: 10.1109/DAC63849.2025.11132861

access: closed

type: Conference or Workshop Paper

metadata version: 2025-09-23

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/dac/WangFWWLJSH25
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/dac/WangFWWLJSH25
Zhican Wang, Hongxiang Fan, Haroon Waris, Gang Wang, Zhenyu Li, Jianfei Jiang, Yanan Sun, Guanghui He:
VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and Dataflow-flexible Accelerator. DAC 2025: 1-7

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.