Checked fact 320630 Oct 2026Research

The paper says the output distribution is the same as sampling from the target model alone, for any approximation model, with no retraining or architecture changes needed.

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

Speculative sampling, and therefore speculative decoding, guarantee an identical output distribution for any choice of approximation model Mq without restriction ... Our method can accelerate existing off-the-shelf models without retraining or architecture changes.

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 the output distribution is the same as sampling from the target model alone, for any approximation model, with no retraining or architecture changes needed.” ai notis, checked 30 Oct 2026. Source: Fast Inference from Transformers via Speculative Decoding (arXiv (Leviathan, Kalman, Matias)). https://ainotis.com/c/3206

As a reference (APA style)

ai notis. (2026, October 30). The paper says the output distribution is the same as sampling from the target model alone, for any approximation model, with no retraining or architecture changes needed [Checked claim 3206]. ai notis. https://ainotis.com/c/3206

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