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
Actualizado 4/7/2026
Estrellas
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.
Instalación
$ install --globalskills.sh
Uso
Después de instalarlo, puedes usar este skill ejecutando el siguiente comando en tu terminal:
skills use flash-attention