Login / Signup
Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?
Cheng Zhang
Jianyi Cheng
Ilia Shumailov
George A. Constantinides
Yiren Zhao
Published in:
EMNLP (2023)
Keyphrases
</>
bayesian networks
probabilistic inference
databases
inference process
bayesian inference
motion compensation
image sequences
neural network
motion estimation
data structure
discrete cosine transform
decision theoretic
bayesian model
real time
fractal image compression
error correcting codes
bit vector