1.安装依赖
yum -y install epel-release
yum -y install gcc binutils wget
yum -y install kernel-devel
2.禁用Nouveau
检查是否开启Nouveau
lsmod | grep nouveau
注意：无信息输出表示已被禁用无需在操作以下步骤；
echo -e "blacklist nouveau\noptions nouveau modeset=0" > /etc/modprobe.d/blacklist.conf
mv /boot/initramfs-$(uname -r).img /boot/initramfs-$(uname -r).img.bak
dracut /boot/initramfs-$(uname -r).img $(uname -r)
reboot
lsmod | grep nouveau
注意：无任何信息输出表示禁用成功；
3.检查驱动
rpm --import https://www.elrepo.org/RPM-GPG-KEY-elrepo.org
rpm -Uvh http://www.elrepo.org/elrepo-release-7.0-4.el7.elrepo.noarch.rpm
yum -y install https://www.elrepo.org/elrepo-release-7.0-4.el7.elrepo.noarch.rpm
yum -y install nvidia-detect
nvidia-detect -v
# 本来应该显示
This device requires the current....
# 结果显卡太老，显示
Probing for supported NVIDIA devices...
[102b:0534] Matrox Electronics Systems Ltd. G200eR2
[10de:1bb3] NVIDIA Corporation GP104GL [Tesla P4]
This device does not appear to be supported at present
Please report at http://elrepo.org/bugs quoting the output from '/sbin/lspci -nn'
手动下载
https://www.nvidia.cn/Download/index.aspx?lang=cn
4.安装cuda
wget https://developer.download.nvidia.com/compute/cuda/12.1.1/local_installers/cuda-repo-rhel7-12-1-local-12.1.1_530.30.02-1.x86_64.rpm
rpm -i cuda-repo-rhel7-12-1-local-12.1.1_530.30.02-1.x86_64.rpm
yum clean all
yum -y install nvidia-driver-latest-dkms
yum -y install cuda
5.驱动安装
下载驱动
chmod +x NVIDIA-Linux-*.run
sh ./NVIDIA-Linux-*.run -s
./NVIDIA-Linux-*.run --kernel-source-path=/usr/src/kernels/3.10.0-1160.31.1.el7.x86_64 -k $(uname -r)
常见错误
1.安装时报错“ERROR: Unable to find the kernel source tree for the currently running kernel. Please make sure you have installed the kernel source files for your kernel and that they are properly configured; on
Red Hat Linux systems, for example, be sure you have the 'kernel-source' or 'kernel-devel' RPM installed. If you know the correct kernel source files are installed, you may specify the
kernel source path with the '--kernel-source-path' command line option.”
解决办法：
yum -y install epel-release
yum -y install kernel-devel
rpm -qa |grep kernel
./NVIDIA-Linux-*.run --kernel-source-path=/usr/src/kernels/3.10.0-1160.31.1.el7.x86_64 -k $(uname -r)
./NVIDIA-Linux-*.run -no-x-check -no-nouveau-check -no-opengl-files --kernel-source-path=/usr/src/kernels/3.10.0-1160.31.1.el7.x86_64 -k $(uname -r)
ailed to run `/usr/sbin/dkms build -m nvidia -v 460.106.00 -k 3.10.0-1160.el7.x86_64`: Sign command:
/lib/modules/3.10.0-1160.el7.x86_64/build/scripts/sign-file
Binary /lib/modules/3.10.0-1160.el7.x86_64/build/scripts/sign-file not found, modules won't be signed
Error! Your kernel headers for kernel 3.10.0-1160.el7.x86_64 cannot be found at /lib/modules/3.10.0-1160.el7.x86_64/build or
/lib/modules/3.10.0-1160.el7.x86_64/source.
Please install the linux-headers-3.10.0-1160.el7.x86_64 package or use the --kernelsourcedir option to tell DKMS where it's located.
3:37:39 ls
13:37:52 lspci | grep nouveau
13:38:03 gcc --version
13:38:09 cmake --version
13:38:29 yum install build-essential -y
13:38:57 yum install build-essential
13:39:11 yum install gcc
13:40:38 gcc --version
13:40:48 yum install cmake
13:41:08 cmake --version
13:41:40 ls
13:41:47 cd /usr/src/
13:41:47 ls
13:41:51 ./NVIDIA-Linux-x86_64-410.129-diagnostic.run
13:42:38 nvidia-detect -v
13:43:48 uname -r
13:43:51 ls
13:44:33 ./NVIDIA-Linux-x86_64-410.129-diagnostic.run --kernel-source-path=/usr/src/kernels/3.10.0-1160.el7.x86_64
13:45:03 kernel-devel
13:45:11 yum install kernel-devel
13:46:03 ls
13:46:06 cd kernels/
13:46:06 ls
13:46:11 cd ..
13:46:24 ./NVIDIA-Linux-x86_64-410.129-diagnostic.run --kernel-source-path=/usr/src/kernels/3.10.0-1160.31.1.el7.x86_64
13:49:51 nvidia-smi
13:50:11 conda env list
13:51:01 scp 10.20.3.27:/root/Anaconda3-5.0.1-Linux-x86_64.sh ./
13:52:09 ls
13:52:22 mv Anaconda3-5.0.1-Linux-x86_64.sh /home/croot/
13:53:11 bzip2
13:53:17 yum install bzip2
13:53:30 bzip2
13:53:32 bunzip2
14:22:50 sudo rpm -i cuda-repo-rhel7-10.0.130-1.x86_64.rpm
14:23:08 ls
14:23:12 wget https://developer.download.nvidia.com/compute/cuda/repos/rhel7/x86_64/cuda-repo-rhel7-10.0.130-1.x86_64.rpm
14:23:16 ls
14:23:22 sudo rpm -i cuda-repo-rhel7-10.0.130-1.x86_64.rpm
14:23:42 sudo yum clean all
14:24:03 sudo yum install cuda
15:30:52 ls
15:30:55 wget https://developer.nvidia.com/compute/cuda/10.0/Prod/local_installers/cuda_10.0.130_410.48_linux
15:40:40 ls
15:40:54 wget http://developer.download.nvidia.com/compute/cuda/10.0/Prod/patches/1/cuda_10.0.130.1_linux.run
15:40:58 ls
15:41:14 which bash
15:41:26 ll -a
15:41:32 ls
15:41:50 /usr/bin/bash cuda_10.0.130_410.48_linux
15:50:00 ls
15:50:23 which bash
15:50:44 /usr/bin/bash cuda_10.0.130_410.48_linux
