text-generation-inference/server/Makefile
Daniël de Kok 093a27c528
Add support for GPTQ Marlin (#2052)
Add support for GPTQ Marlin kernels

GPTQ Marlin extends the Marlin kernels to support common GPTQ
configurations:

- bits: 4 or 8
- groupsize: -1, 32, 64, or 128
- desc_act: true/false

Using the GPTQ Marlin kernels requires repacking the parameters in the
Marlin quantizer format.

The kernels were contributed by Neural Magic to VLLM. We vendor them
here for convenience.
2024-06-14 09:45:42 +02:00

39 lines
1.4 KiB
Makefile

include Makefile-flash-att
include Makefile-flash-att-v2
include Makefile-vllm
include Makefile-awq
include Makefile-eetq
include Makefile-selective-scan
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 ".[bnb, 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-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