mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-19 22:02:06 +00:00
683ff53fa3
* wip(gaudi): import server and dockerfile from tgi-gaudi fork * feat(gaudi): new gaudi backend working * fix: fix style * fix prehooks issues * fix(gaudi): refactor server and implement requested changes
13 lines
679 B
Plaintext
13 lines
679 B
Plaintext
flash_att_commit := 3a9bfd076f98746c73362328958dbc68d145fbec
|
|
|
|
build-flash-attention:
|
|
if [ ! -d 'flash-attention' ]; then \
|
|
pip install -U packaging ninja --no-cache-dir && \
|
|
git clone https://github.com/HazyResearch/flash-attention.git; \
|
|
fi
|
|
cd flash-attention && git fetch && git checkout $(flash_att_commit) && \
|
|
MAX_JOBS=8 python setup.py build && cd csrc/layer_norm && python setup.py build && cd ../rotary && python setup.py build
|
|
|
|
install-flash-attention: build-flash-attention
|
|
cd flash-attention && git checkout $(flash_att_commit) && MAX_JOBS=8 python setup.py install && cd csrc/layer_norm && python setup.py install && cd ../rotary && python setup.py install
|