Checked fact 320930 Oct 2026Research

In the paper's experiments, where the draft model was typically a couple of orders of magnitude smaller than the target, its cost coefficient c (the time for one run of the draft model divided by the time for one run of the target) was always below 0.05 and often close to 0.

Toned down to what the source says

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

experiments where Mq is typically a couple of orders of magnitude smaller than Mp, c was always less than 0.05 and often negligibly close to 0.

What the source said when we opened it, on 30 Oct 2026.

The source

Fast Inference from Transformers via Speculative Decoding
arXiv (Leviathan, Kalman, Matias) · 2022-11-30

Open the source archived copy

Checked

Checked by the notis newsroom on 30 Oct 2026, against the source above.

In the story

How speculative decoding lets a small model draft and a large one check 30 Oct 2026

Cite this fact

Short permanent address

In a sentence

“In the paper's experiments, where the draft model was typically a couple of orders of magnitude smaller than the target, its cost coefficient c (the time for one run of the draft model divided by the time for one run of the target) was always below 0.05 and often close to 0.” ai notis, checked 30 Oct 2026. Source: Fast Inference from Transformers via Speculative Decoding (arXiv (Leviathan, Kalman, Matias)). https://ainotis.com/c/3209

As a reference (APA style)

ai notis. (2026, October 30). In the paper's experiments, where the draft model was typically a couple of orders of magnitude smaller than the target, its cost coefficient c (the time for one run of the draft model divided by the time for one run of the target) was always below 0.05 and often close to 0 [Checked claim 3209]. ai notis. https://ainotis.com/c/3209

Anyone may quote this address. It does not change; if we correct the story, this page says so.