Different versions of TensorRT get different model inference results on GroundingDino model

Description

I inference the groundingDino model using C++ TensorRT.

For the same model and the same image, TensorRT 8.6 can gets the correct detection boxes.

But when I update TensorRT to 10.4, can't get detection boxes.

Possible model result error caused by TensorRT 10.4, How can I analyze this issue?

By the way, I've tried multiple versions other than 8.6 (eg 9.3, 10.0, 10.1), None of them get detection boxes.

additional information below:

I load the save onnx model via C++ TensorRT and print the information for each layer.

TensorRT 8.6 loaded a model with 21060 layers and TensorRT 10.4 loaded a model with 37921 layers, why is the difference in the number of layers so large?

rt104_layers.txt
rt86_layers.txt

Environment

TensorRT Version: 8.6.1.6 / 10.4.0.26

NVIDIA GPU: GeForce RTX 3090

NVIDIA Driver Version: 535.183.06

CUDA Version: 12.2

Relevant Files

Model link: https://drive.google.com/file/d/1VRHKT7cswtDVXNUUmebbPmBSAOyd-fJN/view?usp=drive_link

Start by comparing rt86_layers.txt and rt104_layers.txt, then reproduce the GroundingDino inference using the linked ONNX model across TensorRT 8.6.1.6 and 10.4.0.26. Check whether the layer-count and detection differences can be isolated to the TensorRT version; done means documenting a reproducible cause or the evidence needed for further investigation.