flash-attn
安装
- conda安装nvcc
conda install nvidia/label/cuda-11.8.0::cuda-nvcc
- 去GitHub查看release,拷贝相对应的链接
- Pip 安装
pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu118torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl