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

flash_att_commit := 4d87e4d875077ad9efd25030efa4ab0ba92c19e1

install-flash-attention:
	# Install specific version of flash attention
	pip install packaging
	pip uninstall flash_attn rotary_emb dropout_layer_norm -y || true
	rm -rf flash-attention || true
	git clone https://github.com/HazyResearch/flash-attention.git
	cd flash-attention && git checkout $(flash_att_commit)
	cd flash-attention && python setup.py install && cd csrc/layer_norm && python setup.py install && cd ../rotary && python setup.py install