mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-21 23:12:07 +00:00
ad9d6288c8
@Narsil @drbh this will update flash attention v2 and vllm. You will need to re-install them.
26 lines
757 B
Plaintext
26 lines
757 B
Plaintext
vllm-cuda:
|
|
# Clone vllm
|
|
pip install -U ninja packaging --no-cache-dir
|
|
git clone https://github.com/OlivierDehaene/vllm.git vllm
|
|
|
|
build-vllm-cuda: vllm-cuda
|
|
cd vllm && git fetch && git checkout 4bec8cee87f6bb8cebaec297029713cd2082e0b2
|
|
cd vllm && python setup.py build
|
|
|
|
install-vllm-cuda: build-vllm-cuda
|
|
pip uninstall vllm -y || true
|
|
cd vllm && python setup.py install
|
|
|
|
vllm-rocm:
|
|
# Clone vllm
|
|
pip install -U ninja packaging --no-cache-dir
|
|
git clone https://github.com/fxmarty/vllm-public.git vllm
|
|
|
|
build-vllm-rocm: vllm-rocm
|
|
cd vllm && git fetch && git checkout ad9b7c4095ef54419a0533d254f2ad84bd2dfcae
|
|
cd vllm && python setup.py build
|
|
|
|
install-vllm-rocm: build-vllm-rocm
|
|
pip uninstall vllm -y || true
|
|
cd vllm && python setup.py install
|