Skip to navigation
DeepStream Troubleshooting and FAQ

FAQ for DeepStream GitHub Mono-repo

View as Markdown

1. Where is the DeepStream GitHub mono-repo located?

https://github.com/NVIDIA/DeepStream

Starting with DeepStream 9.0, this mono-repo is the unified home for DeepStream source, samples, tools, and skills across x86, Jetson, and SBSA. SDK release packages moved to the mono-repo GitHub release assets in DeepStream 9.1 (see Q3).

2. Where can I download the DeepStream SDK packages?

Starting from DeepStream 9.1, all DeepStream SDK packages are available as release assets on the NVIDIA DeepStream GitHub mono-repo:

https://github.com/NVIDIA/DeepStream/releases/tag/v9.1.0

Navigate to the release corresponding to your DeepStream version and download the required package from the Assets section.

3. Why has DeepStream moved to GitHub for release packages?

The NVIDIA/DeepStream GitHub mono-repo is the unified platform for all DeepStream releases. DeepStream 9.0 introduced the mono-repo as the release channel. Starting from DeepStream 9.1, the mono-repo GitHub releases page is the single place for both the release and all downloadable SDK packages.

4. What packages are available in the DeepStream 9.2 GitHub release assets?

DeepStream 9.2 packages are available from the Assets section of the DeepStream 9.2 release.

  • Full SDK tarballs
    • deepstream_sdk_v9.2.0_x86_64.tbz2 — x86 dGPU
    • deepstream_sdk_v9.2.0_jetson.tbz2 — Jetson
    • deepstream_sdk_v9.2.0_sbsa.tbz2 — ARM SBSA/DGX Spark
  • Full SDK Debian packages
    • deepstream-9.2_9.2.0-1_amd64.deb — x86 dGPU
    • deepstream-9.2_9.2.0-1_arm64.deb — Jetson
  • Binary-only packages — deepstream-binaries-x86 and deepstream-binaries-aarch64, available as tarballs and Debian packages
  • Sample data package — deepstream-sample-data, available as a tarball and Debian package
  • DeepStream Libraries wheel — Python wheel for x86

5. What is the difference between the full DeepStream package and the deepstream-binaries package?

  • Full DeepStream package: Contains the complete SDK — all open-source components and proprietary libraries — for users who want to install DeepStream directly.
  • deepstream-binaries package: Contains only the proprietary binary libraries. This is intended for users who build DeepStream from source using the mono-repo and need only the closed-source components to complement their build.

Components open sourced with DeepStream 9.2

The following components are open source starting with DeepStream 9.2. Architecture columns identify the corresponding runtime files.

Open-source availability does not imply current support, a recommendation to use the component, or a stable public API. Refer to the component documentation and repository license files for support and licensing details.

GStreamer plugins

File/componentx86aarch64
libnvdsgst_visionencoder.soIncludedIncluded
gst-nvdstextembedderIncludedIncluded
libgstnvunixfd.soIncludedNA
libgstnvvideo4linux2.soIncludedNA

Libraries

File/componentx86aarch64
libnvds_3d_alignment_datafilter.soIncludedIncluded
libnvds_3d_common.soIncludedIncluded
libnvds_3d_dataloader_realsense.soIncludedIncluded
libnvds_3d_depth2point_datafilter.soIncludedIncluded
libnvds_3d_depth_datasource.soIncludedIncluded
libnvds_3d_gl_datarender.soIncludedIncluded
libnvds_3d_gles_ensemble_render.soIncludedIncluded
libnvds_3d_glprocess.soIncludedIncluded
libnvds_3d_multisensor_mixer.soIncludedIncluded
libnvds_3d_sensor_fusion_cluster.soIncludedIncluded
libnvds_3d_video_databridge.soIncludedIncluded
libnvds_csvparser.soIncludedIncluded
libnvds_custom_sequence_preprocess.soIncludedIncluded
libnvds_dsanalytics.soIncludedIncluded
libnvds_infercustomparser.soIncludedIncluded
libnvds_inferutils.soIncludedIncluded
libnvds_lidar_custom_postprocess_impl.soIncludedIncluded
libnvds_lidar_custom_preprocess_impl.soIncludedIncluded
libnvds_lidarfilewrite.soIncludedIncluded
libnvds_tritoninferfilter.soIncludedIncluded
libnvdsgst_3d_gst.soIncludedIncluded
libnvdsgst_helper.soIncludedIncluded
libnvdsgst_tensor.soIncludedIncluded
libnvdsgst_sparse4d.soIncludedIncluded
libnvv4l2.soIncludedNA
libnvv4lconvert.soIncludedNA
libnvds_batch_jpegenc.soIncludedIncluded

NA means Not applicable for that architecture.

6. Where can I find the NVIDIA-AI-IOT GitHub repositories in the GitHub mono-repo?

The table below maps the existing NVIDIA-AI-IOT GitHub repository sources to their location within the GitHub mono-repo:

7. Where do I get the DeepStream Libraries Python wheel?

Starting with DeepStream 9.1, the DeepStream Libraries Python wheel is published as a release asset on the mono-repo GitHub releases page, alongside the other SDK packages:

https://github.com/NVIDIA/DeepStream/releases/tag/v9.1.0

Download the wheel (for example deepstream_libraries-1.4-cp312-cp312-linux_x86_64.whl) from the Assets section and install it with pip3 install <wheel>. The DeepStream Libraries source and sample applications are hosted as part of the mono-repo at https://github.com/NVIDIA/DeepStream. See DeepStream Libraries for full setup and usage details.

8. How do I download DeepStream release assets from GitHub using wget or curl?

You can download release assets directly from the command line using curl or wget.

Using curl:

$ curl -LO 'https://github.com/NVIDIA/DeepStream/releases/download/v9.2.0/deepstream-9.2_9.2.0-1_amd64.deb'

Using wget:

$ wget --content-disposition 'https://github.com/NVIDIA/DeepStream/releases/download/v9.2.0/deepstream-9.2_9.2.0-1_amd64.deb'

Replace the filename with the specific asset you want to download from the release page.

9. Where can I download DeepStream SDK packages and container images?

Starting from DeepStream 9.1, all SDK packages are available through the GitHub releases page at https://github.com/NVIDIA/DeepStream/releases/tag/v9.1.0.

DeepStream Docker container images are distributed through ghcr.io/nvidia/deepstream.

10. Where are the DS 9.1 public tar/deb files?

They are now located in the DeepStream mono-repo. See the DS 9.1 release tag:

https://github.com/NVIDIA/DeepStream/releases/tag/v9.1.0

11. Where are current Jetson DeepStream containers published?

The legacy deepstream-l4t container repository will not be updated in future DeepStream releases, though old releases remain accessible to users.

Current Jetson and dGPU container images are distributed through ghcr.io/nvidia/deepstream.

12. Where did the DeepStream Open Source Dockers move to for DS 9.1? (previously https://github.com/NVIDIA-AI-IOT/deepstream_dockers)

https://github.com/NVIDIA/DeepStream

13. Where are DeepStream Skills, auto-magic-calib, and inference-builder located with GitHub Monorepo?

These repos are now also hosted into the mono-repo as listed below:

14. Are there any proprietary files in the DeepStream mono-repo?

Yes, please refer to the EULA file packaged within the proprietary tar/deb released as GitHub Release assets.

The open-source components in the mono-repo are licensed under the Apache License 2.0.

15. I am observing a warning while launching dockers: “groups: cannot find name for group ID 993” or similar. Where does this come from?

This is just a warning. It was introduced in nvidia-container-toolkit 1.19.1-1. For more details, see:

https://github.com/cncf-tags/container-device-interface/issues/175

This applies to all platforms (x86/Jetson/SBSA).

16. How do I build or modify DeepStream components on SBSA / DGX Spark?

Starting with DeepStream 9.2, the SBSA/DGX Spark SDK tarball deepstream_sdk_v9.2.0_sbsa.tbz2 is published in the DeepStream 9.2 release assets.

You can also use the official Docker container, which ships with DeepStream fully installed and all dependencies pre-configured:

https://ghcr.io/nvidia/deepstream

To modify a specific open-source component inside the container, clone the mono-repo and run make only in that component’s directory. Since all prerequisites are already present in the container, there is no need to run the full build/build.sh:

$ git clone https://github.com/NVIDIA/DeepStream.git
$ cd DeepStream/src/<component-directory>
$ make && sudo make install