Overview

This article suggests how to install NVIDIA GPU driver, CUDA Toolkit, NVIDIA Container Toolkit and other NVIDIA software directly from NVIDIA repository on NVIDIA GPU EC2 instances running RHEL (Red Hat Enterprise Linux) or Rocky Linux.

Note that by using this method, you agree to NVIDIA Driver License Agreement, End User License Agreement and other related license agreement. If you are doing development, you may want to register for NVIDIA Developer Program.

Pre-built AMIs

If you need AMIs preconfigured with TensorFlow, PyTorch, NVIDIA CUDA drivers and libraries, consider AWS Deep Learning AMIs. Refer to Release notes for DLAMIs for currently supported options.

For container workloads, consider Amazon ECS-optimized Linux AMIs and Amazon EKS optimized AMIs

Note: instructions in this article are not applicable to pre-built AMIs.

GUI (graphical desktop) remote access

If you need remote graphical desktop access, refer to How do I install GUI (graphical desktop) on Amazon EC2 instances running RHEL/Rocky Linux 8/9?

Note that this article installs NVIDIA Tesla driver (also know as NVIDIA Datacenter Driver), which is intended primarily for GPU compute workloads. If configured in xorg.conf, Tesla drivers support one display of up to 2560x1600 resolution. GRID drivers provide access to four 4K displays per GPU and are certified to provide optimal performance for professional visualization applications.

About CUDA toolkit

CUDA Toolkit is generally optional when GPU instance is used to run applications (as opposed to develop applications) as the CUDA application typically packages (by statically or dynamically linking against) the CUDA runtime and libraries needed.

System Requirements

This article covers the following platforms

• Red Hat Enterprise Linux (RHEL) 9 (x86_64 and arm64)
• Red Hat Enterprise Linux (RHEL) 8 (x86_64 and arm64)
• Rocky Linux 9 (x86_64)
• Rocky Linux 8 (x86_64)

While it may work, NVIDIA do not support Rocky Linux on arm64 architecture or other RHEL compatible Linux OSs such as AlmaLinux. Refer to Driver installation guide for supported kernel versions, compilers and libraries.

Prepare Rocky Linux / RHEL

Launch a new NVIDIA GPU instance preferably with at least 20 GB storage and connect to the instance

Update OS, add EPEL repository, install DKMS, kernel headers and development packages

sudo dnf update -y
OS_VERSION=$(. /etc/os-release;echo $VERSION_ID | sed -e 's/\..*//g')
if ( cat /etc/os-release | grep -q Red ); then
  sudo subscription-manager repos --enable codeready-builder-for-rhel-$OS_VERSION-$(arch)-rpms
elif ( echo $OS_VERSION | grep -q 8 ); then
  sudo dnf config-manager --set-enabled powertools
else
  sudo dnf config-manager --set-enabled crb
fi
sudo dnf install -y https://dl.fedoraproject.org/pub/epel/epel-release-latest-$OS_VERSION.noarch.rpm
sudo dnf install -y dkms kernel-devel kernel-modules-extra unzip gcc make vulkan-devel libglvnd-devel elfutils-libelf-devel xorg-x11-server-Xorg
sudo systemctl enable --now dkms

Restart your EC2 instance if kernel is updated

sudo reboot

Add NVIDIA repository

Configure Network Repo installation

DISTRO=$(. /etc/os-release;echo rhel$VERSION_ID | sed -e 's/\..*//g')
if (arch | grep -q x86); then
  ARCH=x86_64
else
  ARCH=sbsa
fi
sudo dnf config-manager --add-repo http://developer.download.nvidia.com/compute/cuda/repos/$DISTRO/$ARCH/cuda-$DISTRO.repo

Install NVIDIA Driver

To install latest Tesla driver

sudo dnf module install -y nvidia-driver:latest-dkms

To install a specific version, e.g. 565

sudo dnf module install -y nvidia-driver:565-dkms

The above install NVIDIA Proprietary kernel module. Refer to Driver Installation Guide about NVIDIA Kernel Modules and installation options.

Verify

Restart your instance

nvidia-smi

Output should be similar to below

Sat Nov  9 05:06:35 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 565.57.01              Driver Version: 565.57.01      CUDA Version: 12.7     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA T4G                     Off |   00000000:00:1F.0 Off |                    0 |
| N/A   72C    P8             13W /   70W |       1MiB /  15360MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

Optional: CUDA Toolkit

To install latest CUDA Toolkit

sudo dnf install -y cuda-toolkit

To install a specific version, e.g. 12.6

sudo dnf install -y cuda-toolkit-12-6

Refer to CUDA Toolkit documentation about supported platforms and installation options

Verify

/usr/local/cuda/bin/nvcc -V

Output should be similar to below

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2024 NVIDIA Corporation
Built on Thu_Sep_12_02:27:38_PDT_2024
Cuda compilation tools, release 12.6, V12.6.77
Build cuda_12.6.r12.6/compiler.34841621_0

Post-installation Actions

Refer to NVIDIA CUDA Installation Guide for Linux for post-installation actions before CUDA Toolkit can be used. For example, you may want to include /usr/local/cuda/bin to your PATH variable as per Post-installation Actions: Mandatory Actions

Optional: NVIDIA Container Toolkit

NVIDIA Container toolkit supports RHEL on both x86_64 and arm64. For arm64, use g5g.2xlarge or larger instance size as g5g.xlarge may cause failures due to the limited system memory.

To install latest NVIDIA Container Toolkit

sudo dnf install -y nvidia-container-toolkit

Refer to NVIDIA Container toolkit documentation about supported platforms, prerequisites and installation options

Verify

nvidia-container-cli -V

Output should be similar to below

cli-version: 1.17.0
lib-version: 1.17.0
build date: 2024-10-31T09:20+0000
build revision: 63d366ee3b4183513c310ac557bf31b05b83328f
build compiler: gcc 4.8.5 20150623 (Red Hat 4.8.5-44)
build platform: aarch64
build flags: -D_GNU_SOURCE -D_FORTIFY_SOURCE=2 -DNDEBUG -std=gnu11 -O2 -g -fdata-sections -ffunction-sections -fplan9-extensions -fstack-protector -fno-strict-aliasing -fvisibility=hidden -Wall -Wextra -Wcast-align -Wpointer-arith -Wmissing-prototypes -Wnonnull -Wwrite-strings -Wlogical-op -Wformat=2 -Wmissing-format-attribute -Winit-self -Wshadow -Wstrict-prototypes -Wunreachable-code -Wconversion -Wsign-conversion -Wno-unknown-warning-option -Wno-format-extra-args -Wno-gnu-alignof-expression -Wl,-zrelro -Wl,-znow -Wl,-zdefs -Wl,--gc-sections

Container engine configuration

Refer to NVIDIA Container Toolkit documentation about container engine configuration.

Install and configure Docker

To install and configure docker

if (cat /etc/os-release | grep -q Rocky); then
  USER="rocky"
else
  USER="ec2-user"
fi

sudo dnf config-manager --add-repo https://download.docker.com/linux/rhel/docker-ce.repo
sudo dnf install -y docker-ce docker-ce-cli containerd.io
sudo usermod -aG docker $USER
sudo systemctl enable docker

sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

Verify Docker engine configuration

To verify docker configuration

sudo docker run --rm --runtime=nvidia --gpus all public.ecr.aws/docker/library/rockylinux:9 nvidia-smi

Output should be similar to below

Unable to find image 'public.ecr.aws/docker/library/rockylinux:9' locally
9: Pulling from docker/library/rockylinux
4c81ef64b3e1: Pull complete
Digest: sha256:d7be1c094cc5845ee815d4632fe377514ee6ebcf8efaed6892889657e5ddaaa6
Status: Downloaded newer image for public.ecr.aws/docker/library/rockylinux:9
Sat Nov  9 05:15:02 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 565.57.01              Driver Version: 565.57.01      CUDA Version: 12.7     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA T4G                     Off |   00000000:00:1F.0 Off |                    0 |
| N/A   48C    P8             11W /   70W |       1MiB /  15360MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

Install NVIDIA driver, CUDA toolkit and NVIDIA container toolkit installation on EC2 instance at launch

To install NVIDIA driver, CUDA toolkit and NVIDIA container toolkit including Docker when launching a new GPU instance, you can use the following as user data script.

#!/bin/bash
sudo dnf update -y

OS_VERSION=$(. /etc/os-release;echo $VERSION_ID | sed -e 's/\..*//g')
if ( cat /etc/os-release | grep -q Red ); then
  sudo subscription-manager repos --enable codeready-builder-for-rhel-$OS_VERSION-$(arch)-rpms
elif ( echo $OS_VERSION | grep -q 8 ); then
  sudo dnf config-manager --set-enabled powertools
else
  sudo dnf config-manager --set-enabled crb
fi
sudo dnf install -y https://dl.fedoraproject.org/pub/epel/epel-release-latest-$OS_VERSION.noarch.rpm

sudo dnf install -y dkms kernel-devel kernel-modules-extra unzip gcc make vulkan-devel libglvnd-devel elfutils-libelf-devel xorg-x11-server-Xorg
sudo systemctl enable --now dkms

DISTRO=$(. /etc/os-release;echo rhel$VERSION_ID | sed -e 's/\..*//g')
if (arch | grep -q x86); then
  ARCH=x86_64
else
  ARCH=sbsa
fi
sudo dnf config-manager --add-repo http://developer.download.nvidia.com/compute/cuda/repos/$DISTRO/$ARCH/cuda-$DISTRO.repo

sudo dnf module install -y nvidia-driver:latest-dkms

sudo dnf install -y cuda-toolkit

if (cat /etc/os-release | grep -q Rocky); then
  USER="rocky"
else
  USER="ec2-user"
fi
sudo dnf config-manager --add-repo https://download.docker.com/linux/rhel/docker-ce.repo
sudo dnf install -y docker-ce docker-ce-cli containerd.io
sudo systemctl enable docker
sudo usermod -aG docker $USER

sudo dnf install -y nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

sudo reboot

Verify

Connect to your EC2 instance

nvidia-smi
/usr/local/cuda/bin/nvcc -V
nvidia-container-cli -V
sudo docker run --rm --runtime=nvidia --gpus all public.ecr.aws/docker/library/rockylinux:9 nvidia-smi

View /var/log/cloud-init-output.log to troubleshoot any installation issues.

Perform post-installation actions in order to use CUDA toolkit. To verify integrity of installation, you can download, compile and run CUDA samples such as deviceQuery.

Other software

AWS CLI

To install AWS CLI (AWS Command Line Interface) v2 through Snap

sudo dnf install -y snapd
sudo systemctl enable --now snapd snapd.socket
sudo ln -s /var/lib/snapd/snap /snap
sudo snap install aws-cli --classic

Verify

Log off and log in so that your PATH variables are updated correctly.

aws --version

Output should be similar to below

aws-cli/2.19.4 Python/3.12.6 Linux/5.14.0-427.42.1.el9_4.aarch64 exe/aarch64.rhel.9

SSM Agent

To install SSM agent for Session Manager access

if (arch | grep -q x86); then
  sudo dnf install -y https://s3.amazonaws.com/ec2-downloads-windows/SSMAgent/latest/linux_amd64/amazon-ssm-agent.rpm
else
  sudo dnf install -y https://s3.amazonaws.com/ec2-downloads-windows/SSMAgent/latest/linux_arm64/amazon-ssm-agent.rpm
fi

This requires EC2 instance to have attached IAM role with the AmazonSSMManagedInstanceCore managed policy

EC2 Instance Connect

To install EC2 Instance Connect for secure SSH access

cd /tmp
if (arch | grep -q x86); then
  ARCH=amd64
else
  ARCH=arm64
fi
if ( cat /etc/os-release | grep -q 8\. ); then
  curl -L -O https://amazon-ec2-instance-connect-us-west-2.s3.us-west-2.amazonaws.com/latest/linux_$ARCH/ec2-instance-connect.rhel8.rpm
  curl -L -O https://amazon-ec2-instance-connect-us-west-2.s3.us-west-2.amazonaws.com/latest/linux_amd64/ec2-instance-connect-selinux.noarch.rpm
  sudo dnf install -y ./ec2-instance-connect.rhel8.rpm ./ec2-instance-connect-selinux.noarch.rpm
else
  curl -L -O https://amazon-ec2-instance-connect-us-west-2.s3.us-west-2.amazonaws.com/latest/linux_$ARCH/ec2-instance-connect.rpm
  curl -L -O https://amazon-ec2-instance-connect-us-west-2.s3.us-west-2.amazonaws.com/latest/linux_amd64/ec2-instance-connect-selinux.noarch.rpm
  sudo dnf install -y ./ec2-instance-connect.rpm ./ec2-instance-connect-selinux.noarch.rpm
fi
sudo systemctl restart sshd

Allow inbound SSH traffic in your security group

cuDNN (CUDA Deep Neural Network library)

To install cuDNN for the latest available CUDA version.

sudo dnf install -y zlib cudnn

Refer to cuDNN documentation about installation options and support matrix

NCCL (NVIDIA Collective Communication Library)

To install latest NCCL

sudo dnf install -y libnccl libnccl-devel libnccl-static

Refer to NCCL documentation about installation options

DCGM (NVIDIA Data Center GPU Manager)

To install latest DCGM

sudo dnf install -y datacenter-gpu-manager

Refer to DCGM documentation for more information

Verify

dcgmi -v

Output should be similar to below

Version : 3.3.8
Build ID : 43
Build Date : 2024-09-03
Build Type : Release
Commit ID : be8d66b4318e1d5d6e31b67759dc924d1bc18681
Branch Name : rel_dcgm_3_3
CPU Arch : aarch64
Build Platform : Linux 4.15.0-180-generic #189-Ubuntu SMP Wed May 18 14:13:57 UTC 2022 x86_64
CRC : 93724fdcffc34a2656865a161c2d79df

Fabric Manager

To install latest Fabric Manager

sudo dnf install -y nvidia-fabric-manager

To install a specific version, e.g. 565

sudo dnf install -y nvidia-fabricmanager-565

Refer to Fabric Manager documentation for supported platforms and installation options

Verify

nv-fabricmanager -v

Output should be similar to below

Fabric Manager version is : 565.57.01