hf_text-generation-inference/server/Makefile

39 lines
1.8 KiB
Makefile

gen-server:
# Compile protos
pip install grpcio-tools==1.49.1 --no-cache-dir
mkdir text_generation/pb || true
python -m grpc_tools.protoc -I../proto --python_out=text_generation/pb --grpc_python_out=text_generation/pb ../proto/generate.proto
find text_generation/pb/ -type f -name "*.py" -print0 -exec sed -i -e 's/^\(import.*pb2\)/from . \1/g' {} \;
touch text_generation/pb/__init__.py
install-transformers:
# Install specific version of transformers
rm transformers || true
rm transformers-46d37bece7d3ffdef97b1ee4a3170c0a0627d921 || true
curl -L -O https://github.com/huggingface/transformers/archive/46d37bece7d3ffdef97b1ee4a3170c0a0627d921.zip
unzip 46d37bece7d3ffdef97b1ee4a3170c0a0627d921.zip
rm 46d37bece7d3ffdef97b1ee4a3170c0a0627d921.zip
mv transformers-46d37bece7d3ffdef97b1ee4a3170c0a0627d921 transformers
cd transformers && python setup.py install
install-safetensors:
# Install specific version of safetensors
pip install setuptools_rust
rm safetensors || true
rm safetensors-634deccbcbad5eaf417935281f8b3be7ebca69c5 || true
curl -L -O https://github.com/huggingface/safetensors/archive/634deccbcbad5eaf417935281f8b3be7ebca69c5.zip
unzip 634deccbcbad5eaf417935281f8b3be7ebca69c5.zip
rm 634deccbcbad5eaf417935281f8b3be7ebca69c5.zip
mv safetensors-634deccbcbad5eaf417935281f8b3be7ebca69c5 safetensors
cd safetensors/bindings/python && python setup.py develop
install-torch:
# Install specific version of torch
pip install torch --extra-index-url https://download.pytorch.org/whl/cu116 --no-cache-dir
install: gen-server install-torch install-transformers install-safetensors
pip install pip --upgrade
pip install -e . --no-cache-dir
run-dev:
python -m torch.distributed.run --nproc_per_node=2 text_generation/cli.py serve bigscience/bloom-560m --sharded