Sign in
Speculative Streaming: Fast LLM Inference without Auxiliary Models.
Nikhil Bhendawade
Irina Belousova
Qichen Fu
Henry Mason
Mohammad Rastegari
Mahyar Najibi
Published in:
CoRR (2024)
Keyphrases
</>
random fields
artificial intelligence
real time
bayesian networks
image sequences
prior knowledge
probabilistic model
statistical model
mathematical models
accurate models