the open
    research
    Contribute
    Back to the reading lists

    Deep learning· 2023

    AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

    Ji Lin (first author) · 2023 · published 2024

    Read the original

    arXiv 2306.00978OpenAlex W4379260375

    On the reading lists

    Why it matters

    Protected activation-salient weight channels, enabling accurate low-bit LLM inference across devices.

    Condensed from the expert lists' notes.

    The record

    First released
    2023 (from arXiv 2306.00978)
    Published
    2024
    Citations
    1,957 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.355 · computed rank 463 · consensus 0.31, must-read 0, citations percentile 0.75 (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.