Manually Install, Update, and Uninstall AI Workbench on Jetson (Remote)#
Learn how to manually install, update, or remove NVIDIA AI Workbench on a Jetson system.
Agree to the NVIDIA AI Product Agreement
Before downloading or installing, please read the NVIDIA AI Product Agreement, the NVIDIA AI Workbench Shared Security Model, and our Data Privacy Policy.
By downloading, installing, or using the NVIDIA AI Workbench software, you agree to the terms of the NVIDIA AI Product Agreement (EULA). If you do not agree to the terms of the EULA, you are not authorized to download, install, or use NVIDIA AI Workbench. Before downloading and using NVIDIA AI Workbench, please read our Shared Security Model.
Overview of Installing on Jetson#
Using Jetson, you must install AI Workbench using the CLI. You cannot install the Desktop App.
Prerequisites for Your Jetson System#
You need to meet the following requirements to remotely install AI Workbench CLI on a Jetson system:
System resources:
500 MB of disk space for the AI Workbench application
30-40 GB of disk space for containers
16 GB of RAM
Basic Steps#
The basic steps to install AI Workbench on a Jetson system are as follows:
Enable SSH access to the Jetson device
Install AI Workbench on the Jetson device using the CLI
Resolve a Docker compatibility issue with JetPack
Add your local AI Workbench to the remote Jetson where you installed the CLI
Install AI Workbench CLI to a a Jetson System#
You can add your Jetson Nano as a remote development location for AI Workbench by following these steps:
Configure SSH Access to the Jetson Device#
To configure SSH access to the Jetson device, follow these steps:
Get the Jetson device’s IP Address by running:
ifconfig
Look for an interface that includes:
flags=4163<UP,BROADCAST,RUNNING,MULTICAST>
, and note theinet
address (e.g.,192.168.40.125
) because you will need it laterInstall and Configure SSH by running:
sudo apt update && sudo apt install openssh-server
Allow Required Ports (UFW) by running:
sudo ufw enable && sudo ufw allow 10000 && sudo ufw allow 10001
Test the SSH Connection from Local Device to the Jetson#
You can test the SSH connection from your local device to the Jetson by following these steps:
Setup SSH access from your local device (e.g., laptop, PC, or Mac)
Follow SSH key generation steps in the Remote Locations Guide if needed.
Open a new terminal
Check for Existing SSH Keys by running the following command:
ls -la ~/.ssh/
If keys don’t exist, create them by running the following command:
ssh-keygen -t rsa
Add your private key to the SSH agent by running the following commands:
eval "$(ssh-agent -s)" ssh-add ~/.ssh/id_rsa
Copy your public key to the Jetson Nano by running the following command:
ssh-copy-id jetson-username@jetson-ip-address
Test SSH access by running the following command:
ssh jetson-username@jetson-ip-address
Install AI Workbench CLI on Jetson#
Run these commands on the Jetson:
mkdir -p $HOME/.nvwb/bin && \
curl -L https://workbench.download.nvidia.com/stable/workbench-cli/$(curl -L -s https://workbench.download.nvidia.com/stable/workbench-cli/LATEST)/nvwb-cli-Linux-arm64 --output $HOME/.nvwb/bin/nvwb-cli && \
chmod +x $HOME/.nvwb/bin/nvwb-cli && \
sudo -E $HOME/.nvwb/bin/nvwb-cli install
Fix Docker Compatibility Issue on Jetson#
Due to known issues with JetPack and newer Docker versions:
Create the configuration file:
sudo mkdir -p /etc/systemd/system/docker.service.d sudo nano /etc/systemd/system/docker.service.d/jetson-docker.conf
Add the following content:
[Service] Environment="DOCKER_INSECURE_NO_IPTABLES_RAW=1"
Reload and restart Docker:
sudo systemctl daemon-reload sudo systemctl restart docker.service
Add your Jetson device as a Remote Location using AI Workbench#
You can add your Jetson using the AI Workbench Desktop App or CLI. To add your Jetson device as a remote using AI Workbench, follow the steps in the Remote Locations Guide.
FAQs#
To see FAQs relating to this topic, see Ubuntu remote FAQs.
Next Steps#
Do a Quickstart
Learn the Concepts