anijain2305 opened a new pull request #5066: [ConvertLayout] Support QNN ops. URL: https://github.com/apache/incubator-tvm/pull/5066 Recently introduced Op strategy has disabled conversion from NHWC to NCHW in AlterOpLayout (which is correct thing to do). We can solve this problem by calling ConvertLayout in the parser if needed. However, this only works for FP32. For quantized models, parsers give a QNN graph. And this QNN graph goes to relay.build. Relay build internally calls QNN Legalize passes to convert it to Relay-only ops. The problem is ConvertLayout does not work on QNN ops. Therefore, even if we call ConvertLayout after parser, the layouts will not change. This PR implements ConvertLayout for QNN ops. In addition, I have changed the interface of FInferCorrectLayout to ingest an array of Relay Types instead of shapes. This is helpful in operators like Concatenate where we need to know the number of input data tensors. @icemelon9 @zhiics @yzhliu
---------------------------------------------------------------- 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] With regards, Apache Git Services
