vllm 源码构建过程

1. 使用conda创建虚拟环境

conda create -n venv_name python=3.10 -y
conda activate venv_name

2. 从原始仓库clone最新版本的代码:

git clone https://github.com/vllm-project/vllm.git

3. 确保正确设置环境变量

export CUDA_HOME=/usr/local/cuda
export CUDA_NVCC_EXECUTABLE=/usr/local/cuda/bin/nvcc
export CUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda
export PATH=${CUDA_TOOLKIT_ROOT_DIR}/bin:$PATH
cd vllm

4. 安装依赖

pip install -r requirements-cuda.txt

5. 安装包

pip install -e .