Description

Segmentation fault after logModelInfo for dummy ONNX model with contents starting with the letter d.

The logged ONNX IR version is 0.0.0 which appears to be illegal, but not checked: https://github.com/onnx/onnx/blob/main/onnx/common/ir_pb_converter.cc#L407C10-L407C20

Environment

TensorRT Version: 10.13.0
ONNX-TensorRT Version / Branch: main
GPU Type: RTX 5060
Nvidia Driver Version: 575.57.08
CUDA Version: 12.9
CUDNN Version: 9.11.0
Operating System + Version: Ubuntu 22.04
Python Version (if applicable):
TensorFlow + TF2ONNX Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag): container ubuntu:22.04

Relevant Files

Dockerfile and log from docker run attached.

Steps To Reproduce

• echo "dummy" > test.onnx
• trtexec --onnx=test.onnx --saveEngine=test.engine