1、使用ubuntu 24.04.3LTS desktop版本
2、所有安装选项都使用默认
3、安装完成后
(1)开启ssh
sudo apt update
sudo apt install ssh
sudo /etc/init.d/ssh start
(2)补充安装一些常用的软件
sudo apt install wget net-tools build-essential
(3)下载nvidia驱动并安装
https://www.nvidia.cn/drivers/details/250688/
sudo dpkg -i nvidia-driver-local-repo-ubuntu2404-570.172.08_1.0-1_amd64.deb
(4)禁用 Nouveau 驱动并重启
sudo vi /etc/modprobe.d/blacklist.conf
在最后增加一行
blacklist nouveau
sudo update-initramfs -u
sudo reboot
4、打开系统软件：附加驱动
使用nvidia-driver-570-server，应用更改
5、安装nvcc
sudo apt install nvidia-cuda-toolkit
sudo apt update && sudo apt install -y wget gnupg2
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu$(lsb_release -rs | tr -d .)/x86_64/cuda-keyring_1.1-1_all.deb
sudo dpkg -i cuda-keyring_1.1-1_all.deb
echo “deb [signed-by=/usr/share/keyrings/cuda-archive-keyring.gpg] https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64/ /” | sudo tee /etc/apt/sources.list.d/cuda.list
sudo apt install cuda-toolkit-12-8
6、安装cudnn
下载https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/linux-x86_64/cudnn-linux-x86_64-9.8.0.87_cuda12-archive.tar.xz
sudo ln -s /usr/local/cuda-12.8 /usr/local/cuda
cd cudnn-linux-x86_64-9.8.0.87_cuda12-archive/
sudo cp include/cudnn*.h /usr/local/cuda-12.8//include
sudo cp lib/libcudnn* /usr/local/cuda-12.8/lib64
sudo chmod a+r /usr/local/cuda-12.8/include/cudnn*.h /usr/local/cuda-12.8/lib64/libcudnn*
7、安装vllm
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
chmod +x Miniconda3-latest-Linux-x86_64.sh
./Miniconda3-latest-Linux-x86_64.sh
conda create -n vllm python=3.12 -y
conda activate vllm
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
pip install vllm
vllm serve Qwen/Qwen3-8B