Hello,
I use Jetson Orin Nx and Jetpack 6.2. When I run python it gets:
import onnxruntime
exit()
free(): invalid pointer
Aborted (core dumped)
When I run also import kornia, error gets again. But when ı run import torch, it doesnt seem. Why and how can I solve it?
I realize that kornia and onxxruntime is which are after installed torch, torchvision and torchaudio. Other libraries that before installed torch have no error.
error gets update:
import onnxruntime
free(): invalid next size (fast)
Aborted (core dumped)
Hi,
Which package do you use?
You can find all our packages for JetPack 6.2 below (including ONNXRuntime and PyTorch):
Thanks.
Hello @AastaLLL ,
I use onnxruntime-gpu-1.22.0 from jp6/cu126 index . I realized that when I use power on 15W, it gets this error but when I use on MAXN, error disappears. Why is this?
Hi,
Do you meet the same issue as the below topic:
• Hardware Platform (Jetson / GPU) : NVIDIA Jetson AGX Orin
• DeepStream Version : 7.1
• JetPack Version (valid for Jetson only) : 6.1
• TensorRT Version : 10.3
• Issue Type( questions, new requirements, bugs) : question
Hello,
I have an ONNX model stored on my Nvidia Jetson device. I successfully converted it to a TensorRT engine, but before integrating it into a DeepStream pipeline, I would like to test the ONNX model independently.
However, when attempting to create an ONNX Runtime ses…
The issue might be related to the active CPU number under 15W and MAXN.
Thanks.
@AastaLLL
Thank you, can this ‘invalid pointer’ error cause any problem? Can I use my device on 15W?
Hi,
You can run your app to see if it can work correctly.
In our experience, this is related to the CPU number as we disable some CPU nodes under 15W mode.
But in a general GPU workload, it should be fine.
Thanks.
system
Closed
June 4, 2025, 1:23am
10
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.