Checked fact 320530 Oct 2026Research

The paper says each target run yields at least one new token and up to gamma+1 tokens.

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

That way, each parallel run of the target model Mp will produce at least one new token ... but it can potentially generate many new tokens, up to γ + 1, depending on how well Mq approximates Mp.

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

“The paper says each target run yields at least one new token and up to gamma+1 tokens.” ai notis, checked 30 Oct 2026. Source: Fast Inference from Transformers via Speculative Decoding (arXiv (Leviathan, Kalman, Matias)). https://ainotis.com/c/3205

As a reference (APA style)

ai notis. (2026, October 30). The paper says each target run yields at least one new token and up to gamma+1 tokens [Checked claim 3205]. ai notis. https://ainotis.com/c/3205

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