Login / Signup
LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference.
Qichen Fu
Minsik Cho
Thomas Merth
Sachin Mehta
Mohammad Rastegari
Mahyar Najibi
Published in:
CoRR (2024)
Keyphrases
</>
contextual information
context sensitive
databases
context aware
cost effective
computationally expensive
database
real world
case study
bayesian networks
data streams
dynamic environments
inference engine
tree construction