mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-10-16 18:35:23 +00:00
10 lines
513 B
Plaintext
10 lines
513 B
Plaintext
|
flash_att_commit := 221670026643da10fa18391eb995ef6d9b407530
|
||
|
|
|
||
|
|
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
|