flash-attention
Fast and memory-efficient exact attention algorithm.
Fast and memory-efficient exact attention algorithm.
To install this package, run one of the following:
Summary
Fast and memory-efficient exact attention algorithm.
Last Updated
Mar 26, 2025 at 17:07
License
Apache-2.0
Total Downloads
34
Supported Platforms
GitHub Repository
https://github.com/Dao-AILab/flash-attention