RuntimeError: Quantized cudnn conv2d is currenty limited to groups = 1; received groups =16 , during QAT

quantization
1

what dose it mean , getting erroe during QAT to convert model

model_qat = torch.quantization.convert(quantized_model, inplace=False)

2

the groups argument for this function (Conv2d — PyTorch 2.0 documentation) isn’t supported in the quantized conv2d op.

3

Hey Ankit, (@ANKIT_KUMAR1 )

Did you find any solution to fix this issue ?