Login / Signup
Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference.
Piotr Nawrot
Adrian Lancucki
Marcin Chochowski
David Tarjan
Edoardo M. Ponti
Published in:
CoRR (2024)
Keyphrases
</>
dynamic environments
random access
probabilistic inference
compressed data
artificial intelligence
image processing
compression ratio
bayesian networks
inference engine
data compression
data structure
database
image sequences
case study
information systems
computer vision
neural network
data sets