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 Ubuntu on AWS.

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.

This article applies to Ubuntu Linux on AWS only. Similar articles are available for AL2, AL2023, RHEL/Rocky Linux and Windows.

This article install NVIDIA Tesla driver which does not support G6f instances with fractional GPUs. Refer to this article about NVIDIA GRID driver install.

Other Options

If you need AMIs preconfigured with NVIDIA GPU driver, CUDA, other NVIDIA software, and optionally PyTorch or TensorFlow framework, consider AWS Deep Learning AMIs. Refer to Release notes for DLAMIs for currently supported options, and Deep Learning graphical desktop on Ubuntu Linux with AWS Deep Learning AMI (DLAMI) for graphical desktop setup guidance.

Refer to NVIDIA drivers for your Amazon EC2 instance for NVIDIA driver install options and NVIDIA Driver Installation Guide for Tesla driver installation instructions. You can also install NVIDIA driver from Ubuntu repository.

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.

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

NVIDIA CUDA supports the following platforms

• Ubuntu Linux 24.04 (x86_64 and arm64)
• Ubuntu Linux 22.04 (x86_64 and arm64)

Refer to Driver installation guide for supported kernel versions, compilers and libraries.

Prerequisites

Go to Service Quotas console of your desired Region to verify On-Demand Instance quota value of your desired instance type:

• G instance types: Running On-Demand G and VT instances
• P instance types: Running On-Demand P instances

Request quota increase if the assigned value is less than vCPU count of your desired EC2 instance size. Do not proceed until your applied quota value is equal or higher than your instance type vCPU count

Prepare Ubuntu Linux

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

Update OS, and install DKMS, kernel headers and development packages

sudo apt update
sudo apt upgrade -y
sudo apt autoremove -y
sudo apt install -y dkms linux-headers-aws linux-modules-extra-aws amazon-ec2-utils unzip gcc make libglvnd-dev pkg-config

Restart your EC2 instance if kernel is updated

sudo reboot

Add NVIDIA repository

Configure Network Repo installation

DISTRO=$(. /etc/os-release;echo $ID$VERSION_ID | sed -e 's/\.//g')
if (arch | grep -q x86); then
  ARCH=x86_64
else
  ARCH=sbsa
fi
cd /tmp
curl -L -O https://developer.download.nvidia.com/compute/cuda/repos/$DISTRO/$ARCH/cuda-keyring_1.1-1_all.deb
sudo apt install -y ./cuda-keyring_1.1-1_all.deb
sudo apt update 

If you are installing from AWS China Region, you may be able to replace repository source from https://developer.download.nvidia.com to https://developer.download.nvidia.cn

if (ec2-metadata -z | grep cn-); then
  sudo sed -i "s/nvidia\.com/nvidia\.cn/g" /etc/apt/sources.list.d/cuda-ubuntu*.list
  sudo apt clean
fi

Install NVIDIA Driver

Option 1: NVIDIA repo driver

To install latest Tesla driver from NVIDIA repository

sudo apt install -y nvidia-open 
sudo apt install -y nvidia-xconfig

To install a specific driver branch, e.g. R570 production

sudo apt install -y nvidia-open-570
sudo apt install -y nvidia-xconfig

The above install open-source GPU kernel module which is recommended by NVIDIA (and is different from Nouveau open-source driver). Refer to Driver Installation Guide about NVIDIA Kernel Modules and installation options.

Option 2: Ubuntu repo driver

Alternatively, pre-compiled NVIDIA modules may be available from Ubuntu repository.

sudo apt update
VERSION=$(apt-cache search "nvidia-driver" | grep "^nvidia-driver-.*-server-open" | cut -d"-" -f3 | sort -r | head -1)
sudo apt install -y linux-modules-nvidia-$VERSION-server-open-aws nvidia-headless-no-dkms-$VERSION-server-open nvidia-driver-$VERSION-server-open nvidia-utils-$VERSION-server
sudo apt install -y nvidia-settings

Verify

Restart your instance

nvidia-smi

Output should be similar to below

Sun Aug 10 03:03:55 2025       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.65.06              Driver Version: 580.65.06      CUDA Version: 13.0     |
+-----------------------------------------+------------------------+----------------------+
| 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  Tesla T4                       Off |   00000000:00:1E.0 Off |                    0 |
| N/A   23C    P8             10W /   70W |       0MiB /  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 series, e.g. 12.x

sudo dnf install -y cuda-toolkit-12

To install a specific version, e.g. 12.9

sudo dnf install -y cuda-toolkit-12-9

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) 2005-2025 NVIDIA Corporation
Built on Wed_Jul_16_07:30:01_PM_PDT_2025
Cuda compilation tools, release 13.0, V13.0.48
Build cuda_13.0.r13.0/compiler.36260728_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 modify your PATH environment variable to include /usr/local/cuda/bin.

sed -i '$aexport PATH=\"\$PATH:/usr/local/cuda/bin\"' /home/ubuntu/.bashrc
. /home/ubuntu/.bashrc

For runfile installation, modify LD_LIBRARY_PATH to include /usr/local/cuda/lib

Optional: NVIDIA Container Toolkit

NVIDIA Container toolkit supports Ubuntu 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 apt 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: 1.17.8
lib-version: 1.17.8
build date: 2025-05-30T13:47+00:00
build revision: 6eda4d76c8c5f8fc174e4abca83e513fb4dd63b0
build compiler: x86_64-linux-gnu-gcc-7 7.5.0
build platform: x86_64
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

sudo apt install -y docker.io
sudo usermod -aG docker ubuntu
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/ubuntu/ubuntu:latest nvidia-smi

Output should be similar to below

Unable to find image 'public.ecr.aws/ubuntu/ubuntu:latest' locally
latest: Pulling from ubuntu/ubuntu
49383e68c87b: Pull complete 
Digest: sha256:d983809d3530cab2c793f60beacd2a590889aa3cd9076dd4def9831377bb6526
Status: Downloaded newer image for public.ecr.aws/ubuntu/ubuntu:latest
Sun Aug 10 03:05:05 2025       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.65.06              Driver Version: 580.65.06      CUDA Version: 13.0     |
+-----------------------------------------+------------------------+----------------------+
| 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  Tesla T4                       Off |   00000000:00:1E.0 Off |                    0 |
| N/A   24C    P8             13W /   70W |       0MiB /  15360MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

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

Install on EC2 instance at launch

To install NVIDIA driver and NVIDIA container toolkit including Docker when launching a new GPU instance with at least 20 GB storage, you can use the following as user data script.

Remove # character (except the first line) if you wish to install CUDA toolkit

#!/bin/bash
export DEBIAN_FRONTEND=noninteractive
sudo apt update
sudo apt upgrade -y
sudo apt autoremove -y

sudo apt install -y dkms linux-headers-aws linux-modules-extra-aws unzip gcc make libglvnd-dev pkg-config

DISTRO=$(. /etc/os-release;echo $ID$VERSION_ID | sed -e 's/\.//g')
if (arch | grep -q x86); then
  ARCH=x86_64
else
  ARCH=sbsa
fi
cd /tmp
curl -L -O https://developer.download.nvidia.com/compute/cuda/repos/$DISTRO/$ARCH/cuda-keyring_1.1-1_all.deb
sudo apt install -y ./cuda-keyring_1.1-1_all.deb
sudo apt update

sudo apt install -y nvidia-open
sudo apt install -y nvidia-xconfig

# sudo apt install -y cuda-toolkit
# sed -i '$aexport PATH=\"\$PATH:/usr/local/cuda/bin\"' /home/ubuntu/.bashrc
# .  /home/ubuntu/.bashrc

sudo apt install -y docker.io
sudo usermod -aG docker ubuntu
sudo systemctl enable docker

sudo apt 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/ubuntu/ubuntu:latest 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.

If Docker and NVIDIA container toolkit (but not CUDA toolkit) are installed and configured, you can use CUDA samples container image to validate CUDA driver.

sudo docker run --rm --runtime=nvidia --gpus all nvcr.io/nvidia/k8s/cuda-sample:devicequery

GUI (graphical desktop) remote access

If you need remote graphical desktop access, refer to Install GUI (graphical desktop) on Amazon EC2 instances running Ubuntu Linux

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. Refer to GPU-accelerated graphical desktop on Ubuntu Linux with NVIDIA GRID and Amazon DCV for setup guidance.

Other software

AWS CLI

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

sudo snap install aws-cli --classic

Verify

aws --version

Output should be similar to below

aws-cli/2.27.53 Python/3.13.4 Linux/6.8.0-1029-aws exe/x86_64.ubuntu.24

cuDNN (CUDA Deep Neural Network library)

To install cuDNN for the latest available CUDA version.

sudo apt install -y zlib1g cudnn

Refer to cuDNN documentation about installation options and support matrix

NCCL (NVIDIA Collective Communication Library)

To install latest NCCL

sudo apt install -y libnccl2 libnccl-dev

Refer to NCCL documentation about installation options

DCGM (Data Center GPU Manager)

To install DCGM

CUDA_VERSION=$(nvidia-smi | sed -E -n 's/.*CUDA Version: ([0-9]+)[.].*/\1/p')
sudo apt-get install --yes \
                       --install-recommends \
                       datacenter-gpu-manager-4-cuda${CUDA_VERSION}

Refer to DCGM documentation for more information

Verify

dcgmi --version

Output should be similar to below

dcgmi  version: 4.4.1

GDS (GPUDirect Storage)

To install NVIDIA Magnum IO GPUDirect® Storage (GDS)

sudo apt install -y nvidia-gds

To install for a specific CUDA version, e.g. 13.0

sudo apt install -y nvidia-gds-13-0

Reboot

Reboot after installation is complete

sudo reboot

Verify

To verify module

lsmod | grep nvidia_fs

Output should be similar to below

nvidia_fs             262144  0
nvidia              11481088  3 nvidia_uvm,nvidia_fs,nvidia_modeset

To verify successful installation

/usr/local/cuda/gds/tools/gdscheck -p

Output should be similar to below

 GDS release version: 1.15.1.6   
 libcufile version: 2.12         
 Platform: x86_64   
...
...
 =========                       
 GPU INFO:                      
 =========           
 GPU index 0 NVIDIA A10G bar:1 bar size (MiB):32768 supports GDS, IOMMU State: Disabled          
 ==============                            
 PLATFORM INFO:              
 ==============                    
 IOMMU: disabled             
 Nvidia Driver Info Status: Supported(Nvidia Open Driver Installed)                              
 Cuda Driver Version Installed:  13000
 Platform: g5.xlarge, Arch: x86_64(Linux 6.14.0-1012-aws)                                        
 Platform verification succeeded

Refer to GDS documentation and Driver installation guide for more information

GDRCopy

Magnum IO GDRCopy packages for different CUDA versions can be installed from NVIDIA Developer download site. Alternatively, download and compile from Github

Restart your EC2 instance

sudo reboot

Verify

lsmod | grep gdr

Output should be similar to below

gdrdrv                 28672  0
nvidia              14376960  7 nvidia_uvm,gdrdrv,nvidia_modeset

UFM (Unified Fabric Manager)

P6 instance requires additional configuration as per EC2 and NVIDIA documentation.

To install latest NVIDIA Unified Fabric Manager (UFM)

sudo apt install -y nvidia-fabricmanager
sudo systemctl enable nvidia-fabricmanager

To install specific version, e.g. 570

sudo apt install -y nvidia-fabricmanager-570
sudo systemctl enable nvidia-fabricmanager

Restart your EC2 instance

sudo reboot

Verify

nv-fabricmanager -v
systemctl status nvidia-fabricmanager

Output should be similar to below

Fabric Manager version is : 580.95.05

● nvidia-fabricmanager.service - NVIDIA fabric manager service
     Loaded: loaded (/usr/lib/systemd/system/nvidia-fabricmanager.service; enabled; preset: enabled)
     Active: active (running) since ......... UTC; 1min 4s ago
    Process: 22851 ExecStart=/usr/bin/nvidia-fabricmanager-start.sh --mode start (code=exited, status=0/SUCCESS)
   Main PID: 22881 (nv-fabricmanage)
      Tasks: 18 (limit: 3355442)
     Memory: 38.1M
        CPU: 633ms
     CGroup: /system.slice/nvidia-fabricmanager.service
             └─22881 /usr/bin/nv-fabricmanager -c /usr/share/nvidia/nvswitch/fabricmanager.cfg
.........compute.internal nv-fabricmanager[22881]: Starting nvidia-fabricmanager.service - NVIDIA fabric manager service...
.........compute.internal nv-fabricmanager[22881]: Detected Pre-NVL5 system
.........compute.internal nv-fabricmanager[22881]: Connected to 1 node.
.........compute.internal nv-fabricmanager[22881]: Successfully configured all the available NVSwitches to route GPU NVLink traffic. NVLink Peer-to-Peer support will be enabled once the GPUs are successfully registered with the NVLink fabric.
.........compute.internal nv-fabricmanager[22881]: Started "Nvidia Fabric Manager"
.........compute.internal nv-fabricmanager[22881]: Started nvidia-fabricmanager.service - NVIDIA fabric manager service.

To view GPU fabric registration status

nvidia-smi -q -i 0 | grep -i -A 2 Fabric

Output should be similar to below after the GPU has been successfully registered

    Fabric
        State                             : Completed
        Status                            : Success

Refer to Fabric Manager documentation for supported platforms, and any additional installation or configuration steps