hf_text-generation-inference/server/Makefile-flash-att

16 lines
718 B
Plaintext

flash_att_commit := d478eeec8f16c7939c54e4617dbd36f59b8eeed7
flash-attention:
# Clone flash attention
pip install packaging
git clone https://github.com/HazyResearch/flash-attention.git
build-flash-attention: flash-attention
cd flash-attention && git fetch && git checkout $(flash_att_commit)
cd flash-attention && python setup.py build
cd flash-attention/csrc/rotary && python setup.py build
cd flash-attention/csrc/layer_norm && python setup.py build
install-flash-attention: build-flash-attention
pip uninstall flash_attn rotary_emb dropout_layer_norm -y || true
cd flash-attention && python setup.py install && cd csrc/layer_norm && python setup.py install && cd ../rotary && python setup.py install