mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-21 23:12:07 +00:00
683ff53fa3
* wip(gaudi): import server and dockerfile from tgi-gaudi fork * feat(gaudi): new gaudi backend working * fix: fix style * fix prehooks issues * fix(gaudi): refactor server and implement requested changes
39 lines
1.2 KiB
Makefile
39 lines
1.2 KiB
Makefile
include Makefile-flash-att
|
|
include Makefile-flash-att-v2
|
|
include Makefile-vllm
|
|
include Makefile-awq
|
|
include Makefile-eetq
|
|
include Makefile-selective-scan
|
|
|
|
PROTO_PATH ?= ../proto/v3
|
|
|
|
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_PATH) --python_out=text_generation_server/pb \
|
|
--grpc_python_out=text_generation_server/pb --mypy_out=text_generation_server/pb $(PROTO_PATH)/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: gen-server
|
|
pip install pip --upgrade
|
|
pip install --no-deps -r requirements.txt
|
|
pip install -e "."
|
|
|
|
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
|
|
|
|
install-poetry:
|
|
curl -sSL https://install.python-poetry.org | python3 -
|
|
|
|
update-lock:
|
|
rm poetry.lock
|
|
poetry lock --no-update
|
|
|
|
export-requirements:
|
|
poetry export -o requirements.txt --without-hashes
|