Setup an AWS Linux AMI with NVIDIA-Linux-x86_64 drivers and nvidia-container-toolkit

setup-aws-linux-for-gpu.sh

#!/bin/bash

set -e

# Step-by-Step Installation Guide

# Step 0: Remove existing NVIDIA drivers and CUDA installations
sudo yum erase -y nvidia cuda

# Step 1: Update the system and install dependencies
sudo yum update -y
sudo yum groupinstall -y "Development Tools"
sudo yum install -y kernel-devel-$(uname -r) kernel-headers-$(uname -r) dkms

# Step X: Blacklist the nouveau driver === PROBABLY NOT NEEDED, Step 2.5 is needed instead
# sudo bash -c 'echo "blacklist nouveau" > /etc/modprobe.d/blacklist-nouveau.conf'
# sudo bash -c 'echo "options nouveau modeset=0" >> /etc/modprobe.d/blacklist-nouveau.conf'
# sudo dracut --force

sudo reboot

# Step 2: Download and install the NVIDIA driver
aws s3 cp s3://craigaws.bucket.1/NVIDIA-Linux-x86_64-550.90.07.run .
aws s3 cp s3://craigaws.bucket.1/NVIDIA-Linux-x86_64-550.90.07.run .

wget https://us.download.nvidia.com/XFree86/Linux-x86_64/550.90.07/NVIDIA-Linux-x86_64-550.90.07.run
chmod +x NVIDIA-Linux-x86_64-550.90.07.run

# Step 2.5. bug fix c.f. https://github.com/amazonlinux/amazon-linux-2023/issues/538#issuecomment-1793271091
sudo dnf install kernel-modules-extra


sudo ./NVIDIA-Linux-x86_64-550.90.07.run --dkms -s

# These warning messages are expected:
# WARNING: nvidia-installer was forced to guess the X library path '/usr/lib64' and X module path '/usr/lib64/xorg/modules'; these paths were not queryable from the system.  If X fails to find the
#          NVIDIA X driver module, please install the `pkg-config` utility and the X.Org SDK/development package for your distribution and reinstall the driver.
# WARNING: This NVIDIA driver package includes Vulkan components, but no Vulkan ICD loader was detected on this system. The NVIDIA Vulkan ICD will not function without the loader. Most distributions
#          package the Vulkan loader; try installing the "vulkan-loader", "vulkan-icd-loader", or "libvulkan1" package.



# Step 3: Reboot the instance
sudo reboot

# Step 4: Verify the installation
# After reboot, you can run the following command to verify the installation
nvidia-smi

# Step 5: Install Docker
sudo yum update -y
sudo yum install -y docker
sudo service docker start
sudo usermod -a -G docker ec2-user

docker info

# Step 6: Install NVIDIA Container Toolkit

## Set up the package repository and GPG key:
curl -s -L https://nvidia.github.io/libnvidia-container/stable/rpm/nvidia-container-toolkit.repo | sudo tee /etc/yum.repos.d/nvidia-container-toolkit.repo
sudo yum clean expire-cache
sudo yum update -y

## Install the NVIDIA Container Toolkit:
sudo yum install -y nvidia-container-toolkit

## Restart the Docker daemon to complete the installation:
sudo systemctl restart docker

## Run a test container to verify that the installation was successful:
docker run --rm --gpus all nvidia/cuda:11.0.3-base-ubuntu20.04 nvidia-smi