framework-internalsdevelopment
flash-attention
Optimize transformer attention with Flash Attention — 2-4x speedup, 10-20x memory reduction for long sequences on CUDA GPUs.
maintainer
AlexAI-MCP
Updated 4/7/2026
Stars
62
Forks
14
quick start
Installation and usage
Optimize transformer attention with Flash Attention — 2-4x speedup, 10-20x memory reduction for long sequences on CUDA GPUs.
Installation
$ install --globalskills.sh
Usage
Once installed, you can use this skill by running the following command in your terminal:
skills use flash-attention