hf_text-generation-inference/server/Makefile

33 lines
1.2 KiB
Makefile

include Makefile-flash-att
include Makefile-flash-att-v2
include Makefile-vllm
include Makefile-awq
include Makefile-eetq
unit-tests:
pytest -s -vv -m "not private" tests
gen-server:
# Compile protos
pip install grpcio-tools==1.51.1 mypy-protobuf==3.4.0 'types-protobuf>=3.20.4' --no-cache-dir
mkdir text_generation_server/pb || true
python -m grpc_tools.protoc -I../proto --python_out=text_generation_server/pb \
--grpc_python_out=text_generation_server/pb --mypy_out=text_generation_server/pb ../proto/generate.proto
find text_generation_server/pb/ -type f -name "*.py" -print0 -exec sed -i -e 's/^\(import.*pb2\)/from . \1/g' {} \;
touch text_generation_server/pb/__init__.py
install-megablocks:
pip install git+https://github.com/OlivierDehaene/megablocks@181709df192de9a941fdf3a641cdc65a0462996e
install: gen-server
pip install pip --upgrade
pip install -r requirements_cuda.txt
pip install -e ".[bnb, accelerate, quantize, peft]"
run-dev:
SAFETENSORS_FAST_GPU=1 python -m torch.distributed.run --nproc_per_node=2 text_generation_server/cli.py serve bigscience/bloom-560m --sharded
export-requirements:
poetry export -o requirements_cuda.txt --extras bnb --without-hashes
poetry export -o requirements_rocm.txt --without-hashes