mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-19 22:02:06 +00:00
f9e561eced
* style * update torch * ix issues * fix clone * revert mkl * added custom PA * style * fix style * style * hide env vart * fix mixtral model * add skinny kernel and merge fixes * fixed style * fix issue for sliding window models * addressed review comments * fix import * improved error messag * updated default value * remove import * fix imports after rebase * float16 dep * improve dockerfile * cleaned dockerfile
24 lines
896 B
Plaintext
24 lines
896 B
Plaintext
commit_cuda := d243e9dc7e2c9c2e36a4150ec8e64809cb55c01b
|
|
commit_rocm := 4e0929e6e4fa0a3d09d358715c288020ea9dc247
|
|
build-vllm-cuda:
|
|
if [ ! -d 'vllm' ]; then \
|
|
pip install -U ninja packaging --no-cache-dir && \
|
|
git clone https://github.com/Narsil/vllm.git vllm; \
|
|
fi
|
|
cd vllm && git fetch origin && git checkout $(commit_cuda) && python setup.py build
|
|
|
|
install-vllm-cuda: build-vllm-cuda
|
|
cd vllm && git fetch origin && git checkout $(commit_cuda) && pip install -e .
|
|
|
|
build-vllm-rocm:
|
|
if [ ! -d 'vllm' ]; then \
|
|
pip install -U ninja packaging --no-cache-dir && \
|
|
git clone https://github.com/mht-sharma/vllm.git vllm; \
|
|
fi
|
|
cd vllm && git fetch && git checkout $(commit_rocm) && \
|
|
PYTORCH_ROCM_ARCH="gfx90a;gfx942" python setup.py build
|
|
|
|
install-vllm-rocm: build-vllm-rocm
|
|
cd vllm && git fetch && git checkout $(commit_rocm) && \
|
|
PYTORCH_ROCM_ARCH="gfx90a;gfx942" pip install -e .
|