NGC Catalog
CLASSIC
Welcome Guest
Collections
DeepStream SDK

DeepStream SDK

For contents of this collection and more information, please view on a desktop device.
Description
NVIDIA DeepStream SDK enables developers to build accelerated pipelines for a wide range of use-cases such as IVA, retail, industrial inspection, and many more with minimal development effort.
Curator
NVIDIA
Modified
September 10, 2025
Containers
Sorry, your browser does not support inline SVG.
Helm Charts
Sorry, your browser does not support inline SVG.
Models
Sorry, your browser does not support inline SVG.
Resources
Sorry, your browser does not support inline SVG.

NVIDIA DeepStream SDK

NVIDIA’s DeepStream SDK is a multi-sensor AI-based streaming analytics toolkit for video, image, and audio understanding. DeepStream is an integral part of NVIDIA Metropolis, the platform for building end-to-end services and solutions that transform real-time pixels and sensor data into actionable insights. DeepStream SDK features hardware-accelerated building blocks, called plugins, which bring deep neural networks and other complex processing tasks into a processing pipeline. The DeepStream SDK allows you to focus on building optimized Vision AI applications without having to design complete solutions from scratch.

The DeepStream SDK uses AI to perceive pixels and generate metadata while offering integration from the edge-to-the-cloud. The DeepStream SDK can be used to build applications across various use cases including retail analytics, patient monitoring in healthcare facilities, parking management, optical inspection (AOI), supply chain management (logistics), operations and manufacturing.

What is in the NVIDIA DeepStream SDK Collection

NVIDIA NGC offers collections that easily group relevant information together. We have created the NVIDIA DeepStream SDK collection, so it is easy to find all the information in a single place.

  • DeepStream x86 containers: Containers for Enterprise Grade GPUs. DeepStream is part of NVIDIA AI Enterprise Production Branches.

  • DeepStream Jetson containers: Containers for Thor based systems.

  • DeepStream ARM SBSA container: Container for ARM SBSA based systems.

  • DeepStream Debian Installers: For both x86 and Jetson (ARM) based platforms. These assets are now available under the resource page of NGC. 

  • DeepStream Libraries: For x86 only. These assets allow you to install the DeepStream Libraries from a single python wheel.

  • GXF Runtime and Graph Composer Installers*: GXF runtime is available for both x86 and Jetson. Graph Composer can run on x86 systems running Ubuntu 24.04.

  • TAO Pretrained Models Supported: Details on how to run these models with DeepStream are available in the new Inference Builder GitHub repo, the legacy DeepStream-TAO GitHub repo or the DeepStream documentation.

* NOTE: Be advised that this is the last release of GXF and Graph Composer as part of the DeepStream SDK. Additional information will be provided in the next release of DeepStream.

We have consolidated the DeepStream containers as follows:

Type Architecture Container Name Target
Triton

Multi-Arch

x86 + Jetson

deepstream:8.0-triton-multiarch Development / Deployment
DeepStream Samples

Multi-Arch

x86 + Jetson

deepstream:8.0-samples-multiarch Deployment
DeepStream-ARM-SBSA ARM SBSA deepstream:8.0-triton-arm-sbsa Deployment
Development and Graph Composer x86 deepstream:8.0-gc-triton-devel Development. Includes Graph Composer GUI

NOTE: Some DeepStream dockerfiles are available on GitHub for easy customization.

DeepStream SDK 8.0 Release

For a full list of new features and changes, and known limitations please refer to the DeepStream 8.0 Release Notes.

Key New Features and Enhancements available in DeepStream 8.0:

Category Details
New Features
  • Support for Blackwell and Jetson Thor

  • Support for multi-View 3D Tracking

  • Inference Builder open-source tool to create inference microservices across multiple AI frameworks

  • Support for TAO 6.0 models

Enhancements Please refer to the release notes section of the documentation

Key New Features and Enhancements available on GXF and Graph Composer 5.1

Category Details
New Features

• CUDA Green context

• CPU core pinning

Enhancements • GXF logger as a shared library

Notes:

• DS + Triton graph with CUDA-13.0 on x86 is not support

• Tensorflow backend is not supported in NvTritonExt

• README update /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-can-orientation-app/README

Please refer to the below instructions

  1. Refer to Basler official link and install pylon Camera Software Suite x86 or ARM version from https://www.baslerweb.com/en/products/basler-pylon-camera-software-suite/ Suggest to use pylon_7.2.1 version which is compatible with PSF file 'basler_cam_emulation_0815-0000.pfs'

  2. Download specific pylon 7.2.1 Camera Software Suite Debian packages:

    1. For x86, get them from https://www.baslerweb.com/en/downloads/software-downloads/software-pylon-7-2-1-linux-x86-64bit-debian/

    2. For Jetson, get them from https://www.baslerweb.com/en/downloads/software-downloads/software-pylon-7-2-1-linux-arm-64bit-debian/

Documentation

Item Documentation
Documentation DeepStream SDK Documentation
DeepStream SDK APIs
DeepStream Python APIs
Getting Started

Quick Start Guide
Understanding DeepStream Plugins
Getting Started with Python

Getting Started with Inference Builder
Getting Started with Graph Composer

Developing with C/C++ DeepStream Reference Application (deepstream-app)
Additional DeepStream reference apps
Developing with Python

Python FlowAPIs and Service Maker

Python Application GitHub Repository
Compile and Install Python Bindings
Python Jupyter Notebooks

DeepStream Libraries

Developing with Graph Composer Graph Composer Reference Apps
Graph Composer Apps (GitHub Repo)
DeepStream and TAO Toolkit Integration

TAO Supported Models

DeepStream Inference Builder (GitHub Repo)
DeepStream-TAO Apps (GitHub Repo)
DeepStream Reference Apps (GitHub Repo)

Deep Dives with DeepStream Ninjas DeepStream Multi-Object Trackers
DeepStream Inference Options with Triton and TensorRT
Additional Examples Additional GitHub Repos
Learn More New To DeepStream? Start here
Additional resources on DevZone

Supported Hardware and Software Dependencies

Jetson Series Modules JetPack

Latest

DeepStream Supported

Thor Jetson AGX Thor 7.0 8.0
Orin

Jetson AGX Orin, Jetson Orin NX, Jetson Orin Nano

IGX (including dGPU mode)

6.1 7.1
Xavier Jetson AGX Xavier, Jetson Xavier NX 5.1.3 6.3 (legacy)
TX2 Jetson TX2 NX Jetson TX2 4.6.x 6.0 (legacy)
Nano Jetson Nano 4.6.x 6.0 (legacy)

Enterprise GPU Architecture GPUs
Blackwell B100, B200, RTX PRO Server and Workstation Edition, GB200
Ada Lovelace L4, L40, L40S
Ampere A2, A10, A16, A30, A40, A100, RTX A6000
Hopper H100
Turing T4
Software Dependencies x86 / ARM SBSA Jetson (via JetPack)
Operating System Ubuntu LTS 24.04 Ubuntu LTS 24.04
GStreamer 1.24.2 1.24.2
Rivermax 1.70.32 1.70.32
DLFW (Triton) 25.03 25.08
TensorRT 10.9.0.34 10.13.2.6
CUDA 12.8 13.0
cuDNN 9.7.1 9.12.0
GPU Driver (RM) 570.133.20 580

CV-CUDA

(DeepStream Libraries)

0.15.0-beta N/A

NvImageCodec

(DeepStream Libraries)

0.6.0.32 N/A

PyNvVideoCodec

(DeepStream Libraries)

2.0.0 N/A

Note:

If you are looking for older versions of DeepStream, please refer to the x86 or Jetson archive. Archived documentation is available here.

Technical Support

DeepStream Support is available via:

Method Available to
Forums All developers
Direct Support NVIDIA AI Enterprise License holders

Known Limitations

There are known bugs and limitations in the SDK. To learn more about those, refer to the release notes.

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.