anijain2305 commented on pull request #6119: URL: https://github.com/apache/incubator-tvm/pull/6119#issuecomment-663077305
I realized that this is more of scale calculation instead of quantize or dequantize calculation. Therefore, this should be considered where we are quantizing the model. For QNN dialect, the model is already quantized, so not required. Closing. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
