JetPack 7.2 delivers more value from the same Jetson hardware through software. As agentic AI moves to the edge and memory costs remain a real constraint in production deployments, this release directly addresses both.
Features include one-command deployment of NVIDIA NemoClaw, memory and workflow optimization agent skills for Jetson, official Yocto Project support for lean and reproducible production builds, and MIG on Jetson Thor for deterministic multiworkload execution. With JetPack 7.2, you can do more on existing hardware while building toward increasingly capable agentic workloads at the edge.
NVIDIA has officially released JetPack 7.2, bringing significant improvements in AI performance, system optimization, developer tools, and edge AI capabilities for the NVIDIA Jetson ecosystem. We are excited to announce that JetPack 7.2 is fully supported on the Tanna TechBiz Eagle-201 Carrier Board for NVIDIA® Jetson Orin Nano™ / NX.
For developers, researchers, robotics engineers, and AI solution providers, this means you can immediately take advantage of the newest NVIDIA software stack while leveraging the compact, high-performance, and industrial-ready Eagle-201 platform.
JetPack 7.2 introduces the latest versions of NVIDIA’s AI and acceleration frameworks, making edge AI deployment faster, more efficient, and easier to develop.
These updates are especially valuable for applications involving computer vision, generative AI, autonomous robotics, smart surveillance, and industrial automation.
The Tanna TechBiz Eagle-201 Carrier Board has been validated with JetPack 7.2 on the following modules:
The Eagle-201 carrier board was designed specifically for high-performance edge AI deployments. Its compact 100 mm × 80 mm form factor makes it ideal for space-constrained applications while still offering extensive connectivity.
These capabilities align perfectly with JetPack 7.2’s enhanced support for AI vision, robotics, and real-time inference workloads.
Installing JetPack 7.2 is straightforward. NVIDIA provides installation methods including SDK Manager
With JetPack 7.2 on Eagle-201, developers can expect:
Faster AI model inference: Lower latency and higher throughput
Improved power efficiency: Better thermal and energy management
Better camera pipeline performance: Enhanced vision processing
Enhanced ROS 2 integration: For robotics applications
Optimized TensorRT execution: For large AI models
Smoother multitasking: Across concurrent AI workloads
| Operating System | Jetson Linux | 39.2 |
| Kernel | k6.8 | |
| Distro | L4T Ubuntu 24.04 | |
| Other Supported Linux Distros | Canonical Ubuntu 24.04 for Jetson | |
| AI Compute | NVIDIA CUDA® | 13.2.1 |
| NVIDIA CuDNN | 9.20.0 | |
| NVIDIA TensorRT™ | 10.16.2 | |
| Graphics | Vulkan | 1.4 |
| Vulkan SC | 1.0 | |
| OpenWF DIsplay | Not supported | |
| OpenGL | 4.6 | |
| OpenGLES | 3.2 | |
| GLX | 1.4 | |
| EGL | 1.5 | |
| Multimedia | V4L2 | 1.22.1 |
| Computer Vision | VPI | 4.1.3 |
| PVA | 2.9.1 | |
| NVIDIA Nsight™ Developer Tools | Nsight Systems | 2026.3 |
| Nsight Graphics | 2025.3 | |
| Nsight Deep Learning Designer | 2025.2 | |
| Nsight Perf SDK | 2025.4 | |
| Supported SDKs and Tools | Jetson Platform Services | N/A |
| NVIDIA DeepStream SDK | 8.0 | |
| NVIDIA Isaac™ ROS | Coming soon | |
| NVIDIA Holoscan SDK | 3.9.0 | |
| NVIDIA Triton™ Inference Server | Triton Container | |
| Power Estimator | 2.7 | |
| NVIDIA Container Toolkit | 1.19 (w/ ISO image) |
The release of JetPack 7.2 marks another major step forward for edge AI development on NVIDIA Jetson platforms. By supporting JetPack 7.2 on the Tanna TechBiz Eagle-201 Carrier Board, developers gain immediate access to NVIDIA’s latest AI acceleration technologies without changing their hardware platform.
Whether you are building robots, AI cameras, industrial inspection systems, or next-generation edge AI devices, the Eagle-201 provides a compact, high-performance, and JetPack-ready foundation for your project.