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.
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 |
|
| 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
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'
Download specific pylon 7.2.1 Camera Software Suite Debian packages:
| 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.
DeepStream Support is available via:
| Method | Available to |
|---|---|
| Forums | All developers |
| Direct Support | NVIDIA AI Enterprise License holders |
There are known bugs and limitations in the SDK. To learn more about those, refer to the release notes.
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:
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.