Cite
Notes
Only stored in your browser.
Attribution
Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference
arXiv 2024
from 1 papers
Daniel Korat
Jonathan Mamou
Michal Gordon
Moshe Berchansky
Moshe Wasserblat
Nadav Timor
Oren Pereg
Tomer Galanti