mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-25 20:12:07 +00:00
b2b5df0e94
This PR adds support for AMD Instinct MI210 & MI250 GPUs, with paged attention and FAv2 support. Remaining items to discuss, on top of possible others: * Should we have a `ghcr.io/huggingface/text-generation-inference:1.1.0+rocm` hosted image, or is it too early? * Should we set up a CI on MI210/MI250? I don't have access to the runners of TGI though. * Are we comfortable with those changes being directly in TGI, or do we need a fork? --------- Co-authored-by: Felix Marty <felix@hf.co> Co-authored-by: OlivierDehaene <olivier@huggingface.co> Co-authored-by: Your Name <you@example.com>
30 lines
1.1 KiB
Makefile
30 lines
1.1 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: 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
|