NVIDIA DeepStream SDK is a streaming analytics toolkit for AI-based video and image understanding, providing a GStreamer-based framework to build multi-stream, multi-model inference pipelines on NVIDIA GPUs (dGPU and Jetson).
DeepStream pipelines combine hardware-accelerated decoding/encoding, TensorRT inference, object tracking, and message-broker integrations to deliver real-time video analytics across dGPU and Jetson platforms.
This repository contains the complete source code for DeepStream 9.0.
Components (src/):
src/gst-plugins/— DeepStream GStreamer plugin sourcessrc/utils/— utility library sourcessrc/apps/sample_apps/— GStreamer-based sample applicationssrc/apps/reference_apps/— advanced reference applicationssrc/apps/tao_apps/— TAO-model integration appssrc/service-maker/— Service Maker C++/Python SDK and apps
Tools (tools/):
inference_builder— visual inference pipeline builderauto-magic-calib— camera auto-calibration toolyolo_deepstream— YOLO + TensorRT integrationsam2-onnx-tensorrt— SAM2 ONNX-to-TensorRT conversion
AI agent skills (skills/, for Claude Code & compatible coding agents):
deepstream-dev— general DeepStream developmentdeepstream-generate-pipeline— interactivegst-launchpipeline builderdeepstream-profile-pipeline— Nsight Systems profiling & config derivationdeepstream-sop— SOP step-sequence compliance microservicedeepstream-import-vision-model— autonomous vision-model onboardingamc-setup-calibration-stack— launch the AutoMagicCalib microservice and UIamc-run-sample-calibration— verify AMC with the bundled sample datasetamc-run-video-calibration— calibrate user-provided MP4 camera videos
Before building, ensure the following prerequisites are installed:
- NVIDIA compute stack — driver, CUDA, cuDNN, and TensorRT at the versions listed below. See the DeepStream SDK Installation Guide.
- DeepStream 9.0 — installed via the DS 9.0 public Debian package and its
install.sh.
SBSA / DGX Spark: no DS deb package exists for this platform — use the NVIDIA SBSA Docker container, which bundles the compute stack and DeepStream. See build/BUILD.md.
# Install Git LFS (required for sample video streams used by some apps)
sudo apt-get install git-lfs
# Clone the repo with submodules
git clone --recurse-submodules https://github.com/NVIDIA/DeepStream.git && cd DeepStream
# Pull LFS-tracked files
git lfs install && git lfs pullSee build/BUILD.md for full build instructions, including system package dependencies (x86, aarch64, SBSA / DGX Spark), build/build.sh usage and environment variables (CUDA_VER, NVDS_VERSION), and build output locations under /opt/nvidia/deepstream/deepstream-9.0/.
Supported Platforms
| Platform | Architecture | Notes |
|---|---|---|
| x86 dGPU | x86_64 | Ubuntu 24.04, CUDA 13.1, TensorRT 10.14.x, driver 590+ |
| Jetson | aarch64 | JetPack 7.1 GA (CUDA 13.0, TensorRT 10.13.x) |
| SBSA / DGX Spark | aarch64 | No DS tar/deb package; build and run inside the NVIDIA SBSA Docker container |
# Build. The script prompts for sudo only when installing to system paths.
bash build/build.shAfter bash build/build.sh, binaries are installed to /opt/nvidia/deepstream/deepstream-9.0/bin/. Run the reference deepstream-app with one of the sample configs:
cd /opt/nvidia/deepstream/deepstream-9.0/samples/configs/deepstream-app
deepstream-app -c source30_1080p_dec_infer-resnet_tiled_display.txt
# After the first install, clear the GStreamer plugin cache if needed:
rm -rf ~/.cache/gstreamer-1.0/- More such examples: DeepStream Quickstart Guide
- Detailed API reference: DeepStream SDK Developer Guide
Each app must be run from its source directory so relative config paths resolve correctly. Refer to the README inside each app directory for app-specific run instructions and config options.
Optional. Skip this if the bare-metal build above already works for you. Use the Triton container when you need Triton-backed inference, or when you're on SBSA / DGX Spark (where no native DS deb package exists).
NVIDIA publishes a DeepStream Docker image bundled with Triton Inference Server.
# One-time NGC login (get an API key from https://ngc.nvidia.com)
docker login nvcr.io # username: $oauthtoken, password: <NGC API key>
# Pull the image (use 9.0-triton-arm-sbsa instead on SBSA / DGX Spark)
docker pull nvcr.io/nvidia/deepstream:9.0-triton-multiarch
# Launch with display (use 'fakesink' in your pipeline for headless)
export DISPLAY=:0 && xhost +
docker run -it --rm --gpus all --network=host \
-e DISPLAY=$DISPLAY -v /tmp/.X11-unix/:/tmp/.X11-unix \
nvcr.io/nvidia/deepstream:9.0-triton-multiarch
# Inside the container, run a Triton-backed sample
cd /opt/nvidia/deepstream/deepstream-9.0/samples/configs/deepstream-app-triton
deepstream-app -c source30_1080p_dec_infer-resnet_tiled_display.txtPrerequisites: Docker (docker-ce), the NVIDIA Container Toolkit, NVIDIA driver 590+, and an NGC API key. Triton sample model repos ship under /opt/nvidia/deepstream/deepstream/samples/triton_model_repo/. For gRPC-backed Triton, use samples/configs/deepstream-app-triton-grpc/ instead.
| Page | Description |
|---|---|
| Overview & Architecture | What DeepStream is, key features, and the GStreamer-based pipeline architecture. |
| Release Notes | What's new in this release, supported platforms, and known issues. |
| Installation | Step-by-step installation of the NVIDIA compute stack and DeepStream SDK on x86 and Jetson. |
| Docker Containers | Available DeepStream NGC container images (incl. Triton variants) and how to pull and run them. |
| DeepStream Samples | Reference walkthroughs of the bundled C/C++ sample applications and what each one demonstrates. |
| Reference Applications | Advanced GitHub-hosted reference apps demonstrating specialized end-to-end pipelines. |
| TAO Apps | DeepStream sample apps integrating TAO-trained models (detection, classification, segmentation, pose, LPR). |
| DeepStream Plugins | Reference for every DeepStream GStreamer plugin — properties, pad caps, and usage. |
| Service Maker | Build DeepStream pipelines declaratively with the C++ / Python Service Maker SDK. |
| Inference Builder | Compose and configure DeepStream inference pipelines visually with the Inference Builder tool. |
| Auto Magic Calib | Automatic camera calibration tool for multi-camera DeepStream deployments. |
| DeepStream Coding Agent | Use the bundled skills/ with Claude Code and other AI coding assistants to generate DeepStream pipelines. |
DeepStream/
├── .claude/ # Claude Code project-local config (settings, commands)
├── .github/ # GitHub workflows, issue templates, CODEOWNERS
├── build/
│ ├── BUILD.md # build instructions
│ └── build.sh # top-level build driver
├── example_prompts/ # example prompts for AI coding agents
├── includes/ # shared public headers (ds3d, nvdsinferserver, …)
├── scripts/
│ ├── install_opensource_deps.sh # builds open-source deps (OpenTelemetry, civetweb, …)
│ └── print_env.sh # env diagnostic helper for bug reports
├── skills/
│ ├── amc-run-sample-calibration/ # AMC sample-dataset calibration skill
│ ├── amc-run-video-calibration/ # AMC custom-video calibration skill
│ ├── amc-setup-calibration-stack/ # AMC microservice + UI launch skill
│ ├── deepstream-dev/ # general DS development skill
│ ├── deepstream-generate-pipeline/ # interactive gst-launch pipeline builder
│ ├── deepstream-profile-pipeline/ # Nsight Systems profiling & config derivation
│ ├── deepstream-sop/ # SOP step-sequence compliance microservice
│ └── deepstream-import-vision-model/ # autonomous vision-model onboarding skill
├── src/
│ ├── apps/ # sample, reference, and TAO sample applications
│ ├── gst-plugins/ # GStreamer plugin sources (per-plugin subdirs)
│ ├── gst-utils/ # GStreamer utility library sources
│ ├── service-maker/ # Service Maker C++/Python SDK and apps
│ └── utils/ # utility library sources (per-library subdirs)
└── tools/
├── auto-magic-calib/ # camera auto-calibration tool
├── inference_builder/ # visual inference pipeline builder
├── sam2-onnx-tensorrt/ # SAM2 ONNX-to-TensorRT conversion
└── yolo_deepstream/ # YOLO + TensorRT integration
Summary of benchmarks; for detailed performance numbers and hardware used, refer to the DeepStream Performance Guide.
- Releases/Changelog: CHANGELOG.md
- deepstream_libraries is not currently part of this GitHub OSS repository.
For details and usage, refer to the DeepStream Libraries documentation. - deepstream_dockers is not currently part of this GitHub OSS repository.
For details and usage, refer to the Open Source Dockerfiles Guide.
This project is currently not accepting contributions.
- Vulnerability disclosure: SECURITY.md
- Do not file public issues for security reports.
- Level: Maintained
- How to get help: Issues / Discussions / DeepStream SDK Developer Forum
Join the DeepStream community to ask questions, share feedback, and report issues.
- DeepStream NGC container — prebuilt runtime image (also bundles Triton).
- NVIDIA TAO Toolkit — model training/optimization, source of the TAO sample apps.
- GStreamer documentation — underlying framework.
This project is licensed under CC-BY-4.0 AND Apache-2.0.
- SPDX-License-Identifier: CC-BY-4.0 AND Apache-2.0
Refer THIRD_PARTY_LICENSES for all 3rd Party OSS licenses and Notices