anijain2305 opened a new pull request #4329: [QNN] Use Int16 upcast in Fallback 
Conv2D. Fix test names.
URL: https://github.com/apache/incubator-tvm/pull/4329
 
 
   Before this PR, QNN conv2D Fallback lowering will upcast the data and weight 
to Int32 and then subtract zero points. However, zero points are always 
(u)int8. So, we can safely upcast to just int16 and subtract zero points.
   
   Other fix is for the test names, so that they can be picked up by pytest. 
This was a silly mistake on my side. Adding the fix here.

----------------------------------------------------------------
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

Reply via email to