the open
    research
    Contribute
    Back to the reading lists

    Deep learning· 2022

    Fast Inference from Transformers via Speculative Decoding

    Yaniv Leviathan (first author) · 2022 · published 2023

    Read the original

    arXiv 2211.17192OpenAlex W4310561894

    On the reading lists

    Why it matters

    Enabled faster lossless autoregressive sampling by verifying speculative tokens in parallel.

    Condensed from the expert lists' notes.

    The record

    First released
    2022 (from arXiv 2211.17192)
    Published
    2023
    Citations
    2,196 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.408 · computed rank 354 · consensus 0.63, must-read 0, citations percentile 0.625 (2020s · deep-learning), awards 0, existing lists 0. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.