PagedAttention (vLLM)

Serve far more requests by paging the KV cache like an operating system.

Kwon et al. · SOSP 2023 · Serving. Read the paper ↗

A free, interactive, animated visual explainer of PagedAttention (vLLM) — every exhibit computed from the real formulas, with verbatim quotes from the source.

Questions

What is PagedAttention (vLLM)?
Serve far more requests by paging the KV cache like an operating system.
Who published PagedAttention (vLLM), and where?
Kwon et al. — SOSP 2023 (arXiv:2309.06180).
Where can I find a visual explainer of PagedAttention (vLLM)?
Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.

Related explainers