AndrewZhaoLuo opened a new pull request #8933:
URL: https://github.com/apache/tvm/pull/8933


   This updates the onnx spec for pow up to the latest opset. This includes 
mixing types and having integer pow().
   
   We handle all of this by casting to float since codegen does not support an 
intrinsic pow operator. It might be worth it to come up with a good default 
implementation in relay for integer pow but I do not know if this is going to 
be faster than simply casting.


-- 
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]


Reply via email to