Trtexec Error:Could not find any implementation for node

Please provide the following info (tick the boxes after creating this topic):
Software Version
DRIVE OS 6.0.8.1
DRIVE OS 6.0.6
DRIVE OS 6.0.5
DRIVE OS 6.0.4 (rev. 1)
DRIVE OS 6.0.4 SDK
other

Target Operating System
Linux
QNX
other

Hardware Platform
DRIVE AGX Orin Developer Kit (940-63710-0010-300)
DRIVE AGX Orin Developer Kit (940-63710-0010-200)
DRIVE AGX Orin Developer Kit (940-63710-0010-100)
DRIVE AGX Orin Developer Kit (940-63710-0010-D00)
DRIVE AGX Orin Developer Kit (940-63710-0010-C00)
DRIVE AGX Orin Developer Kit (not sure its number)
other

SDK Manager Version
1.9.3.10904
other

Host Machine Version
native Ubuntu Linux 20.04 Host installed with SDK Manager
native Ubuntu Linux 20.04 Host installed with DRIVE OS Docker Containers
native Ubuntu Linux 18.04 Host installed with DRIVE OS Docker Containers
other

■Problem
When using trtexec to convert ONNX to TensorRT, an error occurs and the conversion fails.

■Error

[06/03/2024-03:44:54] [E] Error[10]: Could not find any implementation for node {ForeignNode[2793…Slice_2457]}.
[06/03/2024-03:44:54] [E] Error[10]: [optimizer.cpp::computeCosts::3897] Error Code 10: Internal Error (Could not find any implementation for node {ForeignNode[2793…Slice_2457]}.)
[06/03/2024-03:44:54] [E] Engine could not be created from network
[06/03/2024-03:44:54] [E] Building engine failed
[06/03/2024-03:44:54] [E] Failed to create engine from model or file.
[06/03/2024-03:44:54] [E] Engine set up failed

■Additional Information
I have confirmed that it works correctly when I run the onnx model.

The TensorRT version on DRIVE OS 6.0.8.1 is 8.6.11.

The execution location is Orin’s /usr/src/tensorrt/bin

How can I solve it?

Dear @HIENG_NS,
Could you share model and trtexec log?

Dear @SivaRamaKrishnaNV

trtexec.log (7.3 KB)
Here is the log

Dear @HIENG_NS,
Can you share trtexec log with verbose flag. Also, is it possible to share your model to verify internally. If model cannot be shared any simple model which can repro the error works for us.

Dear @SivaRamaKrishnaNV
Here is the log with verbose flag
trtexec_verbose.log (4.7 MB)

I will confirm with my team if it is permissible to share the model.

Issue seems to be with fusion of few nodes. If you can provide model which can repro the issue, I can quickly check if got fixed in recent version.

Dear @SivaRamaKrishnaNV
I can share the onnx file, but it is over 100MB in size.
how can i share?

Dear @HIENG_NS,
Your file shared via PM is not accessible. Please use any publicly shared drives like Google drive.

Dear @SivaRamaKrishnaNV
I shared the model with you the other day, Any update on this?

Dear @HIENG_NS,
I see it is failing with internal release as well. I am checking internally and update you.

Dear @SivaRamaKrishnaNV
Thank you for investigating.
Also, if possible, what layers/nodes/plugins should I avoid using in my current environment?