hf_text-generation-inference/server/Makefile

46 lines
1.6 KiB
Makefile

include Makefile-flash-att
include Makefile-flash-att-v2
include Makefile-vllm
include Makefile-awq
include Makefile-eetq
include Makefile-selective-scan
include Makefile-lorax-punica
include Makefile-fbgemm
include Makefile-exllamav2
include Makefile-flashinfer
unit-tests:
pytest -s -vv -m "not private" tests
gen-server:
# Compile protos
pip install grpcio-tools==1.62.2 mypy-protobuf==3.6.0 'types-protobuf' --no-cache-dir
mkdir text_generation_server/pb || true
python -m grpc_tools.protoc -I../proto/v3 --python_out=text_generation_server/pb \
--grpc_python_out=text_generation_server/pb --mypy_out=text_generation_server/pb ../proto/v3/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-server: gen-server
pip install pip --upgrade
pip install -r requirements_cuda.txt
pip install -e ".[accelerate, quantize, peft, outlines]"
install: install-cuda
echo "Installed server"
install-cuda: install-server install-flash-attention-v2-cuda install-vllm-cuda install-flash-attention install-fbgemm
pip install -e ".[bnb,marlin,moe]"
pip install nvidia-nccl-cu12==2.22.3
install-rocm: install-server install-flash-attention-v2-rocm install-vllm-rocm
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 --without-hashes
poetry export -o requirements_rocm.txt --without-hashes
poetry export -o requirements_intel.txt --without-hashes