Checked fact 320430 Oct 2026Research
At the first rejection the later guesses are discarded and the rejected position is resampled from an adjusted distribution; if all guesses are accepted, one extra token is sampled from the target model.
The exact words it rests on
sampling an additional token from an adjusted distribution to fix the first one that was rejected, or to add an additional one if they are all accepted.
What the source said when we opened it, on 30 Oct 2026.
The source
Fast Inference from Transformers via Speculative Decoding
Checked
Checked by the notis newsroom on , 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
Anyone may quote this address. It does not change; if we correct the story, this page says so.