qcd-horizon opened a new pull request #9806:
URL: https://github.com/apache/tvm/pull/9806


   The instance norm epsilon dtype is float32 originally, which will cause 
problem when given a half model. My model, which dtype is float16, uses 
instance norm and failed when extract task from the compuation graph.


-- 
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