Speculative decoding

DISCO

DISCO: Distilling Counterfactuals with Large Language Models

Superseded baseline#98 of 151 most-superseded · first seen Dec 20, 2022

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites DISCO as a baseline.

However, unlike , none of these techniques focus on the data movement cost due to speculation. They require access to output probability distributions and are incompatible with approaches like n-gram speculation.
Utility-Driven Speculative Decoding for Mixture-of-Experts

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.