https://huggingface.co/papers/2601.23180
Paper page - TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
Join the discussion on this paper page
speculative decodingpapervia
https://www.theregister.com/2024/12/15/speculative_decoding/
Intro to speculative decoding: Cheat codes for faster LLMs • The Register
Dec 10, 2024 - Sometimes two models really are faster than one
speculative decodingintrollms
Sponsored https://rencontredouce.com/
RencontreDouce
Less swiping. More actually meeting.
https://huggingface.co/blog/layerskip
Faster Text Generation with Self-Speculative Decoding
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
faster textgenerationself