Zero Zeng

Oh I thought you just use the so compiled from TRT 8.5, @samurdhikaru do you have any comments? Thanks!

Yes, more like a loading issue. NX doesn't have much source.

No, I don't know what change has happen from 8.5 to 9.2. @samurdhikaru Could you please kindly help here ^ ^

Try searching in issues, you'll find some example code.

Your onnx is invalid, it failed with onnxruntime ``` $ polygraphy run model.onnx --onnxrt [I] RUNNING | Command: /home/scratch.zeroz_sw/miniconda3/bin/polygraphy run model.onnx --onnxrt [I] onnxrt-runner-N0-01/12/24-08:07:21 | Activating and starting inference [I]...

Your new model pass with TRT 9.2 ``` [I] Finished engine building in 7.928 seconds [I] trt-runner-N0-01/19/24-09:42:26 ---- Inference Input(s) ---- {input.1 [dtype=float32, shape=(1, 1, 682, 1024)], conv1a.weight [dtype=float32, shape=(64,...

You can download it from https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/9.2.0/tensorrt-9.2.0.5.linux.x86_64-gnu.cuda-11.8.tar.gz https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/9.2.0/tensorrt-9.2.0.5.linux.x86_64-gnu.cuda-12.2.tar.gz https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/9.2.0/tensorrt-9.2.0.5.ubuntu-22.04.aarch64-gnu.cuda-12.2.tar.gz

1. Could you please try latest TRT 8.6/9.2/9.3 release? 2. Could you please try using our official docker container? Cause this looks like a env issue. 3. Please provide the...

We don't fix bug on TRT 8.4 now, could you please try my suggestion? If it still fail then we will fix it in our latest code.

@nvpohanh ^ ^