Login / Signup
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time.
Zichang Liu
Aditya Desai
Fangshuo Liao
Weitao Wang
Victor Xie
Zhaozhuo Xu
Anastasios Kyrillidis
Anshumali Shrivastava
Published in:
NeurIPS (2023)
Keyphrases
</>
query processing
image compression
databases
data compression
test data
statistical tests
software testing
transmission line
mobile devices
test cases
compression ratio
back end