Clarification on Jetpack 6 Jetson Linux and Jetson AI Stack

[nicholas.leong]

Hi all,

I have some questions regarding the latest change in Jetson Linux and Jetson Software stack for Jetpack 6.

My current understanding and assumptions for the previous Jetpack version are that the “AI stack” (cuda, tensorrt etc) is usually tied to the Jetpack or L4T version, and in most cases to upgrade the AI stack we would need to update the base L4T OS as well.

With Jetpack 6, is the idea that we could update the AI stack without updating the Jetson Linux? Or is there a compatibility matrix between the AI stack and Jetson Linux?

What I’m trying to figure out is whether an Orin AGX devkit running Jetpack 6.0 can run a container based on the Jetpack 6.1 AI stack.

[carolyuu]

Hi,
Here are some suggestions for the common issues:

1. Performance

Please run the below command before benchmarking deep learning use case:

$ sudo nvpmodel -m 0
$ sudo jetson_clocks

2. Installation

Installation guide of deep learning frameworks on Jetson:

• TensorFlow: Installing TensorFlow for Jetson Platform - NVIDIA Docs
• PyTorch: Installing PyTorch for Jetson Platform - NVIDIA Docs
  We also have containers that have frameworks preinstalled:
  Data Science, Machine Learning, AI, HPC Containers | NVIDIA NGC

3. Tutorial

Startup deep learning tutorial:

• Jetson-inference: Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson
• TensorRT sample: Jetson/L4T/TRT Customized Example - eLinux.org

4. Report issue

If these suggestions don’t help and you want to report an issue to us, please attach the model, command/step, and the customized app (if any) with us to reproduce locally.

Thanks!

[AastaLLL]

Hi,

Yes, currently Jetson AI Stack can be upgraded without updating Jetson Linux BSP.
Thanks.