Login / Signup
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time.
Zichang Liu
Jue Wang
Tri Dao
Tianyi Zhou
Binhang Yuan
Zhao Song
Anshumali Shrivastava
Ce Zhang
Yuandong Tian
Christopher Ré
Beidi Chen
Published in:
ICML (2023)
Keyphrases
</>
contextual information
artificial intelligence
information systems
cost effective
context sensitive
real time
data sets
neural network
lightweight
sparse representation