hf_text-generation-inference/server/Makefile-flash-att-v2

13 lines
490 B
Plaintext

flash_att_v2_commit := 4f285b354796fb17df8636485b9a04df3ebbb7dc
flash-attention-v2:
# Clone flash attention
pip install packaging
git clone https://github.com/HazyResearch/flash-attention.git flash-attention-v2
build-flash-attention-v2: flash-attention-v2
cd flash-attention-v2 && git fetch && git checkout $(flash_att_v2_commit)
cd flash-attention-v2 && python setup.py build
install-flash-attention-v2: build-flash-attention-v2
cd flash-attention-v2 && python setup.py install