the open
    research
    Contribute
    Back to the reading lists

    Deep learning· 2023

    Efficient Memory Management for Large Language Model Serving with PagedAttention

    Woosuk Kwon (first author) · 2023

    Read the original

    DOI 10.1145/3600006.3613165arXiv 2309.06180OpenAlex W4387321091

    On the reading lists

    Why it matters

    Introduced PagedAttention and vLLM, transforming KV-cache management and high-throughput LLM serving.

    Condensed from the expert lists' notes.

    The record

    First released
    2023 (from arXiv 2309.06180)
    Citations
    9,202 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Also relevant to
    Language, speech & LLMs
    Score
    0.688 · computed rank 80 · consensus 0.83, must-read 1, citations percentile 0.969 (2020s · deep-learning), awards 0, existing lists 0. Method

    Editor's notes

    • Readability check: fail: A specialised serving-systems paper; valuable to engineers, not a lifetime read. (AI draft (Claude), not yet reviewed, 2026-10-29)

    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.