CUDA Toolkit 11.8 introduced a package-upgrade path for supported Jetson systems: developers can install newer CUDA driver interfaces and toolkit components while keeping their existing JetPack version and Jetson Linux board support package (BSP). The change makes CUDA upgrades more flexible, but NVIDIA’s published material does not quantify how much quicker the process is.
What CUDA Toolkit 11.8 changed for Jetson
Before this upgrade path, Jetson’s CUDA driver was packaged with the Jetson Linux BSP, while the toolkit was a separate part of JetPack. Because BSP and desktop CUDA releases did not follow the same schedule, developers could be constrained to the CUDA version bundled with their JetPack release.
CUDA 11.8 added an upgrade package that lets developers update CUDA without replacing an already validated BSP. The package coexists with the default BSP drivers; it does not replace the rest of JetPack. NVIDIA announced the feature on October 4, 2022, describing support for JetPack 5.0 and later. Its Jetson upgrade announcement explains the workflow.
What “easier and quicker” means
The practical improvement is separation: a developer can update CUDA without taking on a full JetPack or BSP upgrade. That can avoid changing a board software stack that has already been validated for a project. NVIDIA calls the process simplified, but its announcement provides no measured before-and-after upgrade time, so a specific time saving cannot be claimed.
#1 Best Overall
- The NVIDIA Jetson AGX Orin 64GB Developer Kit makes it easy to get started with Jetson Orin. Compact size, lots of connectors, and up to 275 TOPS of AI performance make this developer kit perfect for prototyping advanced AI-powered robots and other autonomous machines.
- The developer kit includes a Jetson AGX Orin 64GB module, and can emulate all the Jetson Orin modules. It supports multiple concurrent AI application pipelines with the NVIDIA Ampere GPU architecture, next-generation deep learning and vision accelerators, high-speed IO and fast memory bandwidth. Now you can develop solutions using your largest and most complex AI models to solve problems such as natural language understanding, 3D perception, and multi-sensor fusion.
- Jetson runs the NVIDIA AI software stack, and use-case specific application frameworks are available, including Isaac for robotics, DeepStream for vision AI, and Riva for conversational AI. You can save significant time with NVIDIA Omniverse Replicator for synthetic data generation (SDG), and by using NVIDIA TAO toolkit to fine-tune pretrained AI models from the NGC catalog.
- Jetson ecosystem partners offer additional AI and system software, developer tools, and custom software development. They can also help with cameras and other sensors, as well as carrier boards and design services for your product.
- With the computing capability of more than 8 Jetson AGX Xavier systems in a developer kit that integrates the latest NVIDIA GPU technology with the world’s most advanced deep learning software stack, you’ll have the flexibility to create tomorrow’s AI solution as well as today’s.
The upgrade also does not make every newer CUDA release compatible with every JetPack version. Compatibility depends on the exact CUDA and JetPack combination, and a CUDA upgrade cannot supply unrelated JetPack components that an application needs.
Check compatibility before installing
NVIDIA’s broad announcement names JetPack 5.0 and later, but the exact supported combinations are version-specific. The archived CUDA 11.8 application note lists support for JetPack 5.0.x and describes compatibility between the default 11.4 user-mode driver and CUDA Toolkit 11.8 through minor-version compatibility. Consult the table in NVIDIA’s CUDA for Tegra application note for the release combination you have. It documents CUDA 11.8 behavior; it is not a blanket guarantee for later CUDA releases.
Rank #2
- AGX Orin 64GB Development Kit makes it easy to get started with AGX Orin. Its compact size, rich interfaces, and AI performance of up to 275 TOPS make it ideal for building advanced AI robots and other autonomous machine prototypes.
- The development kit includes AGX Orin 64GB module and can emulate all Orin modules. It utilizes the Ampere GPU architecture, next-generation deep learning and vision accelerators, high-speed I/O, and fast memory bandwidth. You can leverage the largest and most complex AI models to develop solutions for problems such as natural language understanding, 3D perception, and multi-sensor fusion.
- Jetson runs AI software and provides application frameworks for specific use cases, such as Isaac for robotics, DeepStream for visual AI, and Riva for conversational AI. Using Omniverse Replicator for Synthetic Data Generation (SDG) can save you significant time; while fine-tuning pre-trained AI models from the NGC catalog using the TAO toolkit can further enhance your results.
- Yahboom offers four kits for users to choose from. The AIlarge model voice module utilizes examples of AI large models and multimodal models; it provides 1TB/2TB SSDs with pre-flashed driver image files; and an 8MP USB industrial camera for image processing.
- It offers various online and offline mainstream AI large model development materials. The system is pre-configured with AI vision examples, ROS case studies, and AI large models. It supports offline/online deployment of large models for voice interaction, real-time video analysis, and visual positioning, helping you quickly get started with localized AI agent development.
- Confirm your JetPack version and the CUDA upgrade package’s supported combination in the applicable NVIDIA compatibility table.
- Consider whether your application depends on a newer JetPack component or interface in addition to CUDA. NVIDIA warns that such a feature may fail even if the CUDA upgrade installs successfully.
- Plan for only one CUDA upgrade package at a time. Installing another replaces the currently installed upgrade package; an incompatible package fails to install.
How applications use the upgraded CUDA libraries
The aarch64-Jetson installer packages the CUDA Toolkit and upgrade package together. The upgrade libraries are installed in the versioned CUDA directory’s compat subdirectory, alongside the retained BSP drivers. For CUDA 11.8 and later, the upgrade package includes libcuda.so.*, libnvidia-ptxjitcompiler.so.*, and libnvidia-nvvm.so.*.
An application can select the compatibility libraries by adding that directory to LD_LIBRARY_PATH. NVIDIA’s archived CUDA 11.8 example uses this command before running deviceQuery:
Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Scan for outdated or missing drivers - takes under a minute3Repair Windows errors before they cause bigger problemsRank #3
- 【Core Parameters】★AI Perf:34-67 TOPS ★GPU:512-core NVIDIA Ampere architecture GPU with 16 Tensor Cores ★CPU:6-core Arm Corte-A78AE v8.2 64-bit CPU 1.5MB L2 + 4MB L3 ★Memory:4GB 64-bit LPDDR5 51 GB/s ★Storage: external NVMe via M.2 Key M (NOTE:SUB Board No SD Card Slot)
- 【Empowered by Large Al Model, Enhanced Human-Computer Interaction】Jetson Orin Super leverages three AI models and incorporates an AI voice interaction module. This multimodal visual system matches the scene being described, enabling environmental awareness and AI visual gameplay. Combined with a large-scale voice module and camera, it enables speech-to-text, semantic analysis, natural conversation, and real-time video analysis, enabling advanced embodied AI applications.
- 【AI Upgrade】Jetson Orin Nano series modules are compact in size but can deliver up to 34-67 TOPS of AI performance, with power consumption ranging from 7 watts to 25 watts. Compared to the Jetson Nano B01, it offers up to 80 times the performance and sets a new standard for entry-level edge AI.
- 【Highly compatible carrier board】Yahboom's carrier board is fully compatible with orin nano module. Compared to carrier boards that use Jetson Nano on the market, the newly upgraded circuit supports 25W power mode, which enables larger and more complex neural networks and fully leverages the performance of the core module. The resources, size, and interfaces of the Yahboom carrier board are consistent with the official board, with the only difference addition of power switch button.
- 【Tutorial materials provided】The JETSON system based on Ubuntu 22.04 provides a complete desktop Linux environment with accelerated graphics, supporting NVIDI-ACUDA 12.6, TensorRT 10.7.0, cuDNN 9.6.0, OpenCV 4.10.0, etc. The performance on AI LLM, VLM and visual Transformer is significantly improved compared with the previous generation.
export LD_LIBRARY_PATH=/usr/local/cuda-11.8/compat:$LD_LIBRARY_PATH
./deviceQueryIn that documented example, the device is identified as an Orin, the CUDA driver/runtime version is reported as 11.8, and the result is PASS. This is NVIDIA’s example output, not an independent test or a guarantee for every Jetson model. Applications that do not select the compatibility directory continue to have the BSP’s default drivers available.
What the upgrade does—and does not—update
- It updates: CUDA driver interfaces and toolkit components provided by the installed upgrade package.
- It preserves: the existing JetPack version, Jetson Linux BSP, and default BSP drivers.
- It does not update: every other JetPack component or guarantee compatibility with features that require newer non-CUDA interfaces.
- It does not establish: that every CUDA release after 11.8 can be installed on every JetPack release. Check the relevant current NVIDIA compatibility information for versions beyond the archived 11.8 documentation.
Why the documentation’s date matters
NVIDIA’s CUDA Toolkit 11.8 release notes, last updated October 6, 2022, mark package-upgradable CUDA for Jetson as available starting with CUDA 11.8. The CUDA 11.8 release notes and archived application note establish the 11.8 feature and its documented combinations; they should not be read as current compatibility tables for later releases.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
