MX93 segmentation fault in libethosu_delegate.so

hramoser — Wed, 28 May 2025 06:09:23 GMT

We are using the NPU on a MX93 CPU to perform audio processing. The neural network is recurrent with many state variables. Loading such a vela compiled network with tensorflow+libethosu_delegate.so causes a segmentation violation. Networks with less inputs and outputs work fine.
The problem can be easily reproduced on the with the latest OS LF_v6.12.3-1.0.0_images_IMX93EVK. Within python3 execute these commands:

import tflite_runtime.interpreter as tflite

ext_delegate = [tflite.load_delegate("/usr/lib/libethosu_delegate.so")]

interpreter=tflite.Interpreter(model_path='vela_segv.tflite', experimental_delegates=ext_delegate)

interpreter.allocate_tensors()

Any ideas?

Re: MX93 segmentation fault in libethosu_delegate.so

Zhiming_Liu — Fri, 06 Jun 2025 01:44:26 GMT

Hi @hramoser

I did some initial checking and it seems to be related to the library for ethuos delegate. Need to check further.

Best Regards,
Zhiming

topic MX93 segmentation fault in libethosu_delegate.so in i.MX Processors

MX93 segmentation fault in libethosu_delegate.so

Re: MX93 segmentation fault in libethosu_delegate.so