SourceScore

Verified claim · AI-ML · 100% confidence

FlashAttention introduced in paper: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Dao et al., 2022).

Last verified 2026-05-16 · Methodology veritas-v0.1 · e120182d1e01ea2b

Structured fields

Subject
FlashAttention
Predicate
introduced_in_paper
Object
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Dao et al., 2022)
Confidence
100%
Tags
flash-attention · performance · dao · 2022 · stanford

Sources (2)

  1. [1] preprint · arXiv (Dao, Fu, Ermon, Rudra, Ré) · 2022-05-27

    FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
    We propose FlashAttention, an IO-aware exact attention algorithm that uses tiling to reduce the number of memory reads/writes between GPU high bandwidth memory (HBM) and GPU on-chip SRAM.
  2. [2] github release · Dao-AILab · 2022-05-27

    FlashAttention reference implementation

Cite this claim

Ready-to-paste citation (Markdown / plain text):

FlashAttention introduced in paper: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Dao et al., 2022). — SourceScore Claim e120182d1e01ea2b (verified 2026-05-16). https://sourcescore.org/api/v1/claims/e120182d1e01ea2b.json

Embed this claim

Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.

<iframe src="https://sourcescore.org/embed/claim/e120182d1e01ea2b/" width="100%" height="360" frameborder="0" loading="lazy" title="FlashAttention introduced in paper: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Dao et al., 2022)."></iframe>

Preview: open in new tab

Related claims

Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.

Use this claim in your code

Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.

cURL

curl https://sourcescore.org/api/v1/claims/e120182d1e01ea2b.json

JavaScript / TypeScript

const r = await fetch("https://sourcescore.org/api/v1/claims/e120182d1e01ea2b.json"); const envelope = await r.json(); console.log(envelope.claim.statement); // "FlashAttention introduced in paper: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Dao et al., 2022)."

Python

import httpx r = httpx.get("https://sourcescore.org/api/v1/claims/e120182d1e01ea2b.json") envelope = r.json() print(envelope["claim"]["statement"]) # "FlashAttention introduced in paper: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Dao et al., 2022)."

LangChain (retrieve-then-cite)

from langchain_core.tools import tool import httpx @tool def get_flashattention_fact() -> dict: """Fetch the verified SourceScore claim for FlashAttention.""" r = httpx.get("https://sourcescore.org/api/v1/claims/e120182d1e01ea2b.json") return r.json()