Use Aidge Quantization in tensorRT

https://docs.nvidia.com/deeplearning/tensorrt/archives/tensorrt-861/developer-guide/index.html#types-precision

TensorRT is supposed to support ONNX QDQ graph. We should try and check performances versus TensorRT quantization.

added Feature 🚀 label

Linked to: aidge_onnx#61 for support of ONNX QDQ format.

TensorRT documentation about using quantized types are available here