home/categories/framework-internals/alexai-mcp-hermes-ccc-skills-flash-attention-skill-md
framework-internalsdevelopment

flash-attention

Optimize transformer attention with Flash Attention — 2-4x speedup, 10-20x memory reduction for long sequences on CUDA GPUs.

AlexAI-MCP
maintainer
AlexAI-MCP
업데이트됨 4/7/2026
스타
62
포크
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.

설치
$ install --globalskills.sh
사용법

설치 후 터미널에서 다음 명령을 실행하여 이 스킬을 사용할 수 있습니다:

skills use flash-attention