Why does img2img diffusion task not have quantization support? how to get it working with quantization?

Description

In the diffusion demo support matrix it's mentioned that img2img task doesn't have quantization support, why is that? can someone please provide a bit more clarity? If someone can provide a direction to add support for this, I'd be happy to contribute. Is it because of the calibration dataset?

We want to get it working on a realtime usecase and speed up we get from quantization will be crucial.

Environment

TensorRT Version: 10.11.0.33

NVIDIA GPU: RTX 4090

NVIDIA Driver Version: 565.57.01

CUDA Version: 12.7

CUDNN Version:

Operating System:

Python Version (if applicable):

Tensorflow Version (if applicable):

PyTorch Version (if applicable):

Baremetal or Container (if so, version):

Relevant Files

Model link:

Steps To Reproduce

Commands or scripts:

Have you tried the latest release?:

Can this model run on other frameworks? For example run ONNX model with ONNXRuntime (polygraphy run <model.onnx> --onnxrt):