---
title: 'FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is arXiv non-exclusive distribution license (verified on arXiv abs page 2026-11-11); this pointer note is our own words and is CC BY 4.0; we link to the paper rather than reproduce it'
source: https://iinventedlight.com/library/notes/2205-14135-flashattention.md
source_license: 'arXiv non-exclusive distribution license'
attribution: 'Pointer by iinventedlight (AI-assisted). Source: Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, Christopher Ré, FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-11
status: published
approved_by: "Cole Withington, 2026-11-11 20:58 PT, Grok Bot chat widget t1717s7407: \"Publish all 100 including the LLMs Encode Clinical Knowledge note\""
checked_on: 2026-11-11
as_of: 2026-11-11
confidence: medium
untested: 'Pointer note only. Paper not reproduced. Abs page and license checked 2026-11-11.'
category: arxiv
topic_area: 'ai-research: efficiency'
tags: arxiv, attention, efficiency, long-context
arxiv_id: 2205.14135
alias: 2205.14135-flashattention
type: pointer
format: pointer
sources:
  - id: S1
    title: 'FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness'
    publisher: arXiv
    authors: 'Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, Christopher Ré'
    url: https://arxiv.org/abs/2205.14135
    version_read: 'v2 (23 Jun 2022)'
    accessed: 2026-11-11
    license: 'arXiv non-exclusive distribution license'
---
# FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

## Summary
[FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://arxiv.org/abs/2205.14135) (2022) made exact attention much faster and less memory-hungry by taking the GPU memory hierarchy seriously. It does not approximate the attention matrix; it reorders the computation so that fewer reads and writes go to high-bandwidth memory.

What it introduced: an IO-aware exact-attention kernel, with large wall-clock and memory gains on long sequences, which made longer-context Transformer training and inference much more practical.

What it led to: FlashAttention becoming a default kernel in modern training stacks, and a follow-up (FlashAttention-2) pointed to in batch D. Live notes: [hf-transformers-attention-backends](https://iinventedlight.com/library/notes/hf-transformers-attention-backends/). Longer context also connects to [ao-context-long-context-limits](https://iinventedlight.com/library/notes/ao-context-long-context-limits/).

If you are choosing an attention backend or asking why long-context training became feasible, start here. Where to read it: https://arxiv.org/abs/2205.14135 (v2, last revised 23 Jun 2022).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).