varunneal/

flash-attention-hopper

pip install -U pip wheel setuptools ninja numpy packaging psutil
# Any Torch Nightly after 08/30 should be alright
pip install --pre torch==2.10.0.dev20251210+cu130 --index-url https://download.pytorch.org/whl/nightly/cu130

git clone https://github.com/Dao-AILab/flash-attention
cd flash-attention/hopper

export MAX_JOBS=16
export FLASH_ATTENTION_FORCE_BUILD=TRUE        # skip prebuilt wheel fetch
export FLASH_ATTENTION_DISABLE_SM80=TRUE       # Hopper-only
export FLASH_ATTENTION_DISABLE_FP16=TRUE       # leave BF16, FP8


python setup.py bdist_wheel

export FLASH_ATTENTION_TRITON_AMD_ENABLE="TRUE"
export MAX_JOBS=4