ibsidorenko opened a new pull request, #13323: URL: https://github.com/apache/tvm/pull/13323
This commit fixes the following issue: For the sequence of ops qnn.dequantize -> avg_pool2d -> conv2d -> qnn.quantize FQ2I pass inserts qnn.requantize (or cast) to int32 unconditionally before avg_pool2d. As a result fake quantized qnn.conv2d gets input as int32 dtype, but it is forbidden for qnn.conv2d (supports only uint8/int8/int16). This commit disables such behavoir and support int8/uint8 as input dtype for avg_pool2d in compute function. Also this commit fixes bug[#12381](https://github.com/apache/tvm/issues/12381). -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
