hf_text-generation-inference/server/Makefile-vllm

build-vllm-cuda: REPOSITORY=https://github.com/vllm-project/vllm.git
build-vllm-cuda: VLLM_COMMIT=f8a1e39fae05ca610be8d5a78be9d40f5274e5fc
build-vllm-cuda: BRANCH=main
build-vllm-cuda: build-vllm

build-vllm-rocm: REPOSITORY=https://github.com/fxmarty/vllm-public.git
build-vllm-rocm: VLLM_COMMIT=ad9b7c4095ef54419a0533d254f2ad84bd2dfcae
build-vllm-rocm: BRANCH=rotary-no-positions-split-cos-sin
build-vllm-rocm: build-vllm

vllm:
    # Clone vllm
	pip install -U ninja packaging --no-cache-dir
	git clone --single-branch --branch $(BRANCH) $(REPOSITORY) vllm

build-vllm: vllm
	cd vllm && git fetch && git checkout $(VLLM_COMMIT)
	cd vllm && python setup.py build

install-vllm: build-vllm
	pip uninstall vllm -y || true
	cd vllm && python setup.py install