Local AI Glossary

What is FlashAttention?

Source: paperswithcode/flashattention

An IO-aware exact attention algorithm that reduces memory accesses by tiling. 2-4× faster than standard attention with linear memory in sequence length. FlashAttention-2 and -3 are widely used in modern model training and serving.

How FlashAttention fits in the local AI stack

FlashAttention is part of the broader local AI ecosystem. See the related guides, comparisons, and tools below to see how it applies in practice.

See also

Related terms