u99127 opened a new issue #4824: Tflite frontend needs to use zero point of input tensor while lowering qnn.conv2d for padding URL: https://github.com/apache/incubator-tvm/issues/4824 The Tflite frontend ignores the zero point for input tensors when creating a separate pad operation while lowering quantized convolutions. This is fixed by PR #4807 and the tests broken by that are fixed #4816
---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services