NVIDIA JetPack SDK powering the Jetson modules is the most comprehensive solution for building end-to-end accelerated AI applications, significantly reducing time to market.

NVIDIA JetPack includes 3 components:

Jetson Linux: A Board Support Package (BSP) with bootloader, Linux kernel, Ubuntu desktop environment, NVIDIA drivers, toolchain and more. It also includes security and Over-The-Air (OTA) features.

Jetson AI Stack: CUDA Accelerated AI stack which includes a complete set of libraries for acceleration of GPU computing, multimedia, graphics, and computer vision. It supports application frameworks such as Metropolis to build, deploy and scale Vision AI application, Isaac for building high performance robotic applications and Holoscan for building high performance computing applications (HPC) with real time insights and sensor processing capabilities from edge to cloud.

Jetson Platform Services: A collection of ready to use services to accelerate AI application development on Jetson.

JetPack 6

JetPack 6 is the biggest upgrade ever. It not only brings an updated Kernel and updated Ubuntu root file system but also includes novel features never before available on Jetson. JetPack 6 brings the flexibility to run any Linux Kernel and offers wider options of Linux based distros from Jetson ecosystem partners. It also includes the flexibility to update Jetson AI Stack without updating Jetson Linux BSP.

JetPack 6.0

JetPack 6.0 is the first production release of JetPack 6. Previous JetPack 6.0 Developer Preview was for development on Jetson Orin with JetPack 6.0 stack. This JetPack 6.0 release includes Jetson Linux 36.3 which packs Linux Kernel 5.15 and Ubuntu 22.04 based root file system. Jetson AI stack packaged with this JetPack 6 release includes CUDA 12.2, Tensorrt 8.6, cuDNN 8.9 and VPI 3.1. JetPack 6 supports all NVIDIA Jetson Orin modules and developer kits.

Please read below on new features in JetPack 6.

Installing JetPack

SD Card Image Method
Debian Package Method

JetPack can be installed or upgraded using a Debian package management tool running on Jetson. NVIDIA also hosts runtime and development debian meta packages for all JetPack components. The runtime packages do not include samples and documentations while the development packages include these and are intended for development. Users can install full JetPack or only runtime JetPack components over Jetson Linux.

Please refer to JetPack documentation for instructions on the list of debian packages we host. To install Jetpack on top of Jetson Linux 36.3, all you need to do is “apt install nvidia-jetpack

NOTE: APT upgrade from JetPack 5 to JetPack 6 is not supported.

Key Features in JetPack 6.0

Jetson Linux

NVIDIA Jetson Linux 36.3 provides the Linux Kernel 5.15, UEFI based bootloader, Ubuntu 22.04 based root file system, NVIDIA drivers, necessary firmwares, toolchain and more.

JetPack 6.0 includes Jetson Linux 36.3 with following highlights:
(Please refer to release notes for additional details)

  • Production ready software stack
  • Preview of upgradable compute stack to upgrade CUDA, Tensorrt, CUDNN, DLA and VPI without upgrading Jetson Linux. Refer to JetPack documentation for running compute stack from this production release on JetPack 6 Developer Preview.
  • Power Estimator supported for JetPack 6.
  • Pre-built Kernel debian package with PREMPT_RT enabled.
  • Support for upgrading Jetson Orin Nano Developer Kit from JetPack 5 to JetPack 6 without needing a host machine.
  • Over-The-Air (OTA) Update
    • Support for Over-The-Air (OTA) tool to upgrade NVIDIA Jetson Orin based devices from JetPack 5.
  • Security
    • Enabled support for security features, bringing parity with JetPack 5.
  • Power And Performance
    • Enabled support for power features, bringing parity with JetPack 5.
    • Power Estimator supported for JetPack 6.
  • Display
    • Support for Framebuffer console
    • Support for suspend/resume in Display Core Engine (DCE)
  • Multimedia
    • Support for H264 Constrained_Baseline and Constrained_High profiles
    • Dynamic Bitrate Rate, Dynamic FrameRate support for AV1 encoder
    • Dynamic Resolution Change[DRC] support for H264, H265 and AV1 encoder
    • UYVY BT.709 and BT.2020 colorimetry support for video transform

Jetson Platform Services

Jetson Platform Services is a collection of pre-built and cloud-native software services and reference workflows to accelerate AI applications on Jetson. These services are modular, API-driven and can be quickly configured to build Generative AI and other edge applications. There are 15+ services from AI services to system services. The services include:

  • AI Perception Service using DeepStream
  • AI Inference Service for Visual Language Model (VLM)
  • AI Analytics - to process metadata to time-series insights
  • Sensor Management and Storage with VST
  • Redis Message Bus
  • API and IoT Gateway

To demonstrate the capabilities of these services, following reference workflows are included:

  • AI-NVR - complete workflow for AI-based Network video recorder
  • Generative AI workflow for alerting and visual chat
  • Generative AI workflow for zero-shot detection.

Note: Jetson platform services will be released soon (May End). These services can be easily installed via debian package or via SDK Manager.

Linux Distros on Jetson

JetPack includes Jetson Linux out of the box, but Jetson ecosystem partners offer various Linux based Distros on Jetson. They include:

Canonical Ubuntu: Ubuntu 22.04 offered by Canonical. Please refer to this webinar to learn more about Canonical offering on Jetson.

Red Hat: Red Hat Enterprise Linux 9.3 offered by Red Hat

Windriver: Commercial embedded Linux OS from Windriver.

SUSE: SUSE Linux Enterprise Server (SLES) offered by SUSE.

RedHawk: Real Time Linux OS from Concurrent Real-Time for mission critical hard real time applications.

Yocto based distros: Various Yocto based distros and services leveraging meta-tegra are offered by ecosystem partners like Balena, Foundaries.io & TimeSys.


TensorRT is a high performance deep learning inference runtime for image classification, segmentation, and object detection neural networks. TensorRT is built on CUDA, NVIDIA’s parallel programming model, and enables you to optimize inference for all deep learning frameworks. It includes a deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications.

JetPack 6.0 includes TensorRT 8.6.2


NVIDIA DLA hardware is a fixed-function accelerator engine targeted for deep learning operations. It’s designed to do full hardware acceleration of convolutional neural networks, supporting various layers such as convolution, deconvolution, fully connected, activation, pooling, batch normalization, and others

DLA software consists of the DLA compiler and the DLA runtime stack. The offline compiler translates the neural network graph into a DLA loadable binary and can be invoked using NVIDIA TensorRT™. The runtime stack consists of the DLA firmware, kernel mode driver, and user mode driver.

JetPack 6.0 includes DLA 3.14


CUDA Deep Neural Network library provides high-performance primitives for deep learning frameworks. It provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers.

JetPack 6.0 includes cuDNN 8.9.4


CUDA Toolkit provides a comprehensive development environment for C and C++ developers building GPU-accelerated applications. The toolkit includes a compiler for NVIDIA GPUs, math libraries, and tools for debugging and optimizing the performance of your applications.

JetPack 6.0 includes CUDA 12.2.1

Multimedia API

The Jetson Multimedia API package provides low level APIs for flexible application development.

Camera application API: libargus offers a low-level frame-synchronous API for camera applications, with per frame camera parameter control, multiple (including synchronized) camera support, and EGL stream outputs. RAW output CSI cameras needing ISP can be used with either libargus or GStreamer plugin. In either case, the V4L2 media-controller sensor driver API is used.

Sensor driver API: V4L2 API enables video decode, encode, format conversion and scaling functionality. V4L2 for encode opens up many features like bit rate control, quality presets, low latency encode, temporal tradeoff, motion vector maps, and more.

Computer Vision

VPI (Vision Programing Interface) is a software library that provides Computer Vision / Image Processing algorithms implemented on multiple hardware accelerators found on Jetson such as PVA (Programmable Vision Accelerator), GPU, NVDEC(NVIDIA Decoder), NVENC (NVIDIA Encoder), VIC (Video Image Compositor) and so on.

JetPack 6.0 includes VPI 3.1 with following highlights:

  • Support for Erode algorithm on PVA backend
  • Support for Dilate algorithm on PVA backend


JetPack 6.0 includes the following graphics libraries:

  • Vulkan® 1.3
  • Vulkan® SC 1.0
    • Vulkan SC is a low-level, deterministic, robust API that is based on Vulkan 1.2. This API enables state-of-the-art GPU-accelerated graphics and computation that can be deployed in safety-critical systems and that are certified to meet industry functional safety standards. Refer to https://www.khronos.org/vulkansc/ for more information.
    • Vulkan SC can also be invaluable for real-time non safety critical embedded applications. Vulkan SC increases determinism and reduces application size by shifting preparation of the run-time application environment either offline, or into application setup, as much as possible. This includes offline compilation of graphics pipelines that define how the GPU processes data, together with static memory allocation, that together enable detailed GPU control that can be rigorously specified and tested.
    • Vulkan SC 1.0 is evolved from Vulkan 1.2 and includes: the removal of runtime functionality that is not needed in safety-critical markets, an updated design to provide predictable execution times and results, and clarifications to remove potential ambiguity in its operation. For more details see https://www.khronos.org/blog/vulkan-sc-overview
    • Note: Jetson support for Vulkan SC is not safety certified.
    OpenWF™ Display 1.0
    • OpenWF Display is a Khronos API for low overhead interaction with the native display driver on Jetson and allows interaction with Vulkan SC to display images.
    • Note: Jetson support for OpenWF Display is not safety certified.

Nsight Developer Tools

CUDA Toolkit provides a comprehensive development environment for C and C++ developers building high-performance GPU-accelerated applications with CUDA libraries. The toolkit includes Nsight Visual Studio Code Edition, Nsight Eclipse Plugins, debugging and profiling tools including Nsight Compute, and a toolchain for cross-compiling applications

NVIDIA Nsight Systems is a low overhead system-wide profiling tool, providing the insights developers need to analyze and optimize software performance.

NVIDIA Nsight Graphics is a standalone application for debugging and profiling graphics applications.

NVIDIA Nsight Deep Learning Designer is an integrated development environment that helps developers efficiently design and develop deep neural networks for in-app inference.

Nvidia Nsight Perf SDK is a graphics profiling toolbox for Vulkan and OpenGL enabling the collection of GPU performance metrics directly from user application.

Nsight System, Nsight Graphics, Nsight Compute, Nsight Perf SDK are all supported on Jetson Orin modules to assist development for autonomous machines.

JetPack 6.0 includes NVIDIA Nsight Systems v2024.2

JetPack 6.0 includes NVIDIA Nsight Graphics 2023.4

JetPack 6.0 includes NVIDIA Nsight Perf SDK 2023.5

Supported SDKs and Tools

NVIDIA DeepStream SDK is a complete analytics toolkit for AI-based multi-sensor processing and video and audio understanding.

JetPack 6.0 will support DeepStream 7.0 (coming soon in May)

NVIDIA Isaac™ ROS is a collection of hardware-accelerated packages that make it easier for ROS developers to build high-performance solutions on NVIDIA hardware including NVIDIA Jetson.

JetPack 6.0 will support Isaac ROS 3.0 (coming soon in May)

NVIDIA Holoscan is a sensor processing platform that streamlines the development and deployment of AI and high-performance computing (HPC) applications for real-time insights

JetPack 6.0 will support Holoscan SDK 2.0

NVIDIA Triton™ Inference Server simplifies deployment of AI models at scale. Triton Inference Server is open source and supports deployment of trained AI models from NVIDIA TensorRT, TensorFlow and ONNX Runtime on Jetson. On Jetson, Triton Inference Server is provided as a shared library for direct integration with C API.

PowerEstimator is a webapp that simplifies creation of custom power mode profiles and estimates Jetson module power consumption.

Cloud Native

Jetson brings Cloud-Native to the edge and enables technologies like containers and container orchestration. NVIDIA JetPack includes NVIDIA Container Runtime with Docker integration, enabling GPU accelerated containerized applications on Jetson platform.

NVIDIA hosts several container images for Jetson on NVIDIA NGC. Some are suitable for software development with samples and documentation and others are suitable for production software deployment, containing only runtime components. Find more information and a list of all container images at the Cloud-Native on Jetson page.


NVIDIA Jetson modules include various security features including Hardware Root of Trust, Secure Boot, Hardware Cryptographic Acceleration, Trusted Execution Environment, Disk and Memory Encryption, Physical Attack Protection and more. Learn about the security features by jumping to the security section of the Jetson Linux Developer guide.

JetPack 6.0 Security Highlights include:

  • Enabled support for security features bringing parity with JetPack 5.

JetPack Documentation and Webinars




    Visit the NVIDIA Jetson forum for all your questions and issues, where NVIDIA has a dedicated team of Jetson experts to support you.

For older versions of JetPack, please visit the JetPack Archive.