Hugging Face's logo

kernels-community
/
flash-attn3

kernel
Model card Files Community
1
flash-attn3 / README.md
danieldk's picture
danieldk HF Staff
Remove warning
6fff937
preview code
|
raw
history blame contribute delete
394 Bytes
metadata
license: bsd-3-clause
tags:
  - kernel

Flash Attention 3

Flash Attention is a fast and memory-efficient implementation of the attention mechanism, designed to work with large models and long sequences. This is a Hugging Face compliant kernel build of Flash Attention.

Original code here https://github.com/Dao-AILab/flash-attention.