Verified claim · AI-ML · 92% confidence
FlashAttention-2 introduced in paper: FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning (Dao, 2023).
Last verified 2026-05-31 · Methodology veritas-v0.1 · 786f534a9f79a3be
SourceScore rates how reliable a source is to cite — for AI answers and research. This is one verified claim from the catalog.
Structured fields
- Subject
- FlashAttention-2
- Predicate
introduced_in_paper- Object
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning (Dao, 2023)
- Confidence
- 92%
- Tags
- flashattention-2 · flash-attention · attention · gpu · inference · dao · 2023
Sources (3)
[1] preprint · arXiv (Tri Dao — Princeton + Stanford) · 2023-07-17
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning“We propose FlashAttention-2, with better work partitioning to address these issues.”
[2] github release · Dao AI Lab (Dao-AILab) · 2023-07-17
FlashAttention / FlashAttention-2 reference implementation[3] docs · Hugging Face
FlashAttention-2 (Hugging Face Papers)Hugging Face is rated by SourceScore — see its reliability →
Cite this claim
Ready-to-paste citation (Markdown / plain text):
FlashAttention-2 introduced in paper: FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning (Dao, 2023). — SourceScore Claim 786f534a9f79a3be (verified 2026-05-31). https://sourcescore.org/api/v1/claims/786f534a9f79a3be.jsonEmbed 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/786f534a9f79a3be/" width="100%" height="360" frameborder="0" loading="lazy" title="FlashAttention-2 introduced in paper: FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning (Dao, 2023)."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
Grouped-Query Attention (GQA) introduced in paper: GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints (Ainslie et al., 2023).
3e9122ba60a3fe99 · 92% confidence · shares 3 tags (attention, inference, 2023)
FlashAttention introduced in paper: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Dao et al., 2022).
e120182d1e01ea2b · 100% confidence · shares 2 tags (flash-attention, dao)
Mamba state-space model introduced in paper: Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Gu, Dao, 2023).
3518f8aa40cb0d36 · 100% confidence · shares 2 tags (dao, 2023)
vLLM introduced in: Kwon et al. 2023 — high-throughput LLM serving via PagedAttention.
468a9e2c047d8f2f · 100% confidence · shares 2 tags (inference, 2023)
llama.cpp publicly released on: 2023-03-10 by Georgi Gerganov.
2c6ddc094019890c · 100% confidence · shares 2 tags (inference, 2023)
Frequently asked questions
Is the claim "FlashAttention-2 introduced in paper: FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning (Dao, 2023)." verified?
Yes — SourceScore verified this claim with 92% confidence as of 2026-05-31. The verification uses 3 primary sources cross-referenced against the SourceScore methodology (version veritas-v0.1). Full source list + signed JSON envelope linked below.
What is the evidence for "FlashAttention-2 introduced in paper: FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning (Dao, 2023)."?
Evidence comes from 3 primary sources: arXiv (Tri Dao — Princeton + Stanford), Dao AI Lab (Dao-AILab), Hugging Face. Each source is listed below with verbatim excerpts and URLs. The signed JSON envelope at https://sourcescore.org/api/v1/claims/786f534a9f79a3be.json includes an HMAC-SHA256 signature for audit verification.
When was this claim last verified by SourceScore?
Last verified 2026-05-31 under methodology version veritas-v0.1. The signed JSON envelope is dated and cryptographically signed for audit trail. Re-verification cadence depends on the claim type and source freshness.
How can I cite this SourceScore claim in my code or article?
Fetch the signed JSON envelope from https://sourcescore.org/api/v1/claims/786f534a9f79a3be.json which includes the verbatim claim, primary sources, confidence, methodology version, last-verified date, and HMAC-SHA256 signature for audit. The CC-BY-4.0 license permits commercial use with attribution to SourceScore.
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/786f534a9f79a3be.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/786f534a9f79a3be.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "FlashAttention-2 introduced in paper: FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning (Dao, 2023)."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/786f534a9f79a3be.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "FlashAttention-2 introduced in paper: FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning (Dao, 2023)."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_flashattention_2_fact() -> dict:
"""Fetch the verified SourceScore claim for FlashAttention-2."""
r = httpx.get("https://sourcescore.org/api/v1/claims/786f534a9f79a3be.json")
return r.json()