result mismatch between qdq-onnx and tensorrt engine.

Description

i tried to use tensort8.6.1 to convert a onnx model with qdq nodes, however, the output of the converted engine dismatched with that of original onnx.

Environment

TensorRT Version:8.6.1 GA

NVIDIA GPU: Geforce 3060

NVIDIA Driver Version:Driver Version: 535.230.02

CUDA Version: nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:33:58_PDT_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0

CUDNN Version: 8.6.0

Operating System: ubuntu20.04

Python Version (if applicable):3.9.23

Tensorflow Version (if applicable):

PyTorch Version (if applicable):

Baremetal or Container (if so, version):

Relevant Files

Steps To Reproduce

1. trtexec --onnx=quant_base.onnx --saveEngine=quant_base.plan --dumpProfile=true --int8 --fp16 --verbose=true > log.log 2>&1
   quant_base.onnx
2. python _infer.py
   i use randomly generated input to forward onnx and engine, compare their results by calculating cosine similarity.

Start by reproducing the issue with quant_base.onnx using the provided trtexec command, then run _infer.py to compare the ONNX and TensorRT outputs. Check the verbose build log and cosine-similarity result to identify where the QDQ quantization path diverges; done means the mismatch is explained and a verified correction or minimal reproducer is available.