(Re)-implementation of "Prompt Lookup Decoding" by Apoorv Saxena, with extended ideas from LLMA Decoding.
-
Updated
Aug 20, 2024 - Jupyter Notebook
(Re)-implementation of "Prompt Lookup Decoding" by Apoorv Saxena, with extended ideas from LLMA Decoding.
Speculative Decoding on Bandwidth-Bound Hardware
Add a description, image, and links to the prompt-lookup-decoding topic page so that developers can more easily learn about it.
To associate your repository with the prompt-lookup-decoding topic, visit your repo's landing page and select "manage topics."