most citedMagic Pyramid: Accelerating Inference with Early Exiting and Token Pruning

5 citations · 5 across the 2 of their papers we have counts for

collaborators
Showing cs.IRShow all

1 paper · 1 filter

cs.IR2021

Low-Precision Quantization for Efficient Nearest Neighbor Search

Anthony Ko, Iman Keivanloo, Vihan Lakshman +1

Fast k-Nearest Neighbor search over real-valued vector spaces (KNN) is an important algorithmic task for information retrieval and recommendation systems. We present a method for u…