mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-26 12:32:10 +00:00
0ef8c8a97a
* Using the "lockfile". * Revert dummy modifications. * Lock on python 3.11 * Another attempt. * .. * Bad cache hits. * The good old monkey. * How in the world... * We need the launcher still. * . * .. * Attempt #42 * Don't break all other builds. * Mode max. * Applying to other builds.
51 lines
2.3 KiB
Makefile
51 lines
2.3 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-exllamav2
|
|
include Makefile-flashinfer
|
|
|
|
unit-tests:
|
|
pip install -U pip uv
|
|
uv pip install -e ".[dev]"
|
|
pytest -s -vv -m "not private" tests
|
|
|
|
gen-server:
|
|
# Compile protos
|
|
pip install -U pip uv
|
|
uv pip install -r requirements_gen.txt
|
|
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
|
|
|
|
gen-server-raw:
|
|
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
|
|
uv pip install -e ".[accelerate, compressed-tensors, quantize, peft, outlines]"
|
|
|
|
|
|
install: install-cuda
|
|
echo "Installed server"
|
|
|
|
install-cuda: install-server install-flash-attention-v2-cuda install-flash-attention
|
|
uv pip install -e ".[attention,bnb,marlin,moe]"
|
|
uv pip install nvidia-nccl-cu12==2.22.3
|
|
|
|
install-rocm: install-server install-flash-attention-v2-rocm install-vllm-rocm
|
|
|
|
export-requirements:
|
|
uv pip compile pyproject.toml --extra gen -o requirements_gen.txt --python-version 3.11
|
|
uv pip compile pyproject.toml --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines -o requirements_cuda.txt --python-version 3.11
|
|
uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_intel.txt --python-version 3.11
|
|
uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_rocm.txt --python-version 3.11
|