NGC Catalog
CLASSIC
Welcome Guest
Resources
DeepStream

DeepStream

For downloads and more information, please view on a desktop device.
Description
DeepStream SDK delivers a complete streaming analytics toolkit for AI based video and image understanding and multi-sensor processing. (Resources/ TAR and * Debian)
Publisher
NVIDIA
Latest Version
8.0
Modified
September 10, 2025
Compressed Size
2.91 GB

Before You Start

We have introduced a new NGC DeepStream SDK Collection.

This collection serves as a hub for all DeepStream assets. Make sure you check it out!

DeepStream Installers

Please refer to the section below which describes the different DeepStream installers available.

File Name Architecture License Type Notes
deepstream-8.0_8.0.0-1_amd64.deb x86 Deployment

Installer for Debian compatible systems.

Ubuntu 24.04 is the only tested distribution

deepstream-8.0_8.0.0-1_arm64.deb Jetson Deployment Installer for Jetson devices with JetPack 7.0
deepstream_sdk_v8.0.0_x86_64.tbz2 x86 Deployment Tar installer for x86 based systems
deepstream_sdk_v8.0.0_jetson.tbz2 Jetson Deployment Tar installer for Jetson based devices
pyservicemaker-0.0.1-cp310-cp310-linux_x86_64.whl x86 Deployment pyservicemaker wheels are the pip wheels for the python bindings for servicemaker API
pyservicemaker-0.0.1-cp310-cp310-linux_aarch64.whl Jetson Deployment pyservicemaker wheels are the pip wheels for the python bindings for servicemaker API

Read the DeepStream 8.0 Release Notes for full list of features of the release

Getting Started

Download installer(s)

NGC offers three options to download the assets on this resource. Two options are via a command line, and one more via the browser.

Find below details for all options. Please update the name of the file you would like to download (i.e. deepstream-8.0_8.0.0-1_amd64.deb) when using curl or wget.

curl

curl -LO
'https://api.ngc.nvidia.com/v2/resources/nvidia/deepstream/versions/8.0/files/deepstream-8.0_8.0.0-1_amd64.deb'

wget

wget --content-disposition
'https://api.ngc.nvidia.com/v2/resources/nvidia/deepstream/versions/8.0/files/deepstream-8.0_8.0.0-1_amd64.deb'
-O deepstream-8.0_8.0.0-1_amd64.deb

From Browser

If you would like to download individual files from your web browser, please navigate to the File Browser tab, and click on the three dots for different download options as shown below as reference:

Notes:

  • The animation above shows files from an older release. The steps to download single files are applicable to the latest release as well.

  • Please be aware that the Browser (Direct Download) option available on the pull-down button (top-right corner of this page) will download all files in the resource.

Install DeepStream

For details such as software dependencies and installations steps (once you have downloaded the installer(s)), please refer to the DeepStream Installation section of the documentation.

License

The following licenses apply to the DeepStream SDK assets:

Asset Applicable EULA Notes
SDK DeepStream SDK EULA A copy of the license is available on the following folder of the SDK:
/opt/nvidia/deepstream/deepstream-8.0/LicenseAgreement.pdf
Containers DeepStream NGC License License grants redistribution rights allowing developers to build applications on top of the DeepStream containers
Development Containers DeepStream NGC Development License A development-only license. Does not allow redistribution of the container
TAO Models NVIDIA AI Product License All TAO pre-trained models included in the DeepStream SDK are covered by the NVIDIA AI Product License.

NOTE: By pulling, downloading, or using the DeepStream SDK, you accept the terms and conditions of the EULA licenses listed above.

Ethical AI

NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.