Update Readme for torch_quant_to_onnx.py example

Signed-off-by: ajrasane <[email protected]>

Author: ajrasane

examples/onnx_ptq/README.md

@@ -152,6 +152,8 @@ python torch_quant_to_onnx.py \
     --onnx_save_path=<path to save the exported ONNX model>
 ```
 
+> *Note: TensorRT has limited support for Convolution layers with certain precision formats. FP8 Convolution layers have restrictions on filter sizes and channel dimensions. This example is primarily targeted towards models with Transformer-like architectures (e.g., ViT) which rely mainly on attention mechanisms rather than convolution operations.*
+
 ### Evaluation
 
 If the input model is of type image classification, use the following script to evaluate it.