comaniac commented on pull request #9782:
URL: https://github.com/apache/tvm/pull/9782#issuecomment-999106968
Yeah we shouldn't have such dependency as running SimplifyInference or
SimplifyExpr are not the hard requirement of ToMixedPrecision. One way I could
think of is putting ToMixedPrecision into the compiler pass sequence, but only
apply it via `PassContext(config={"ToMixedPrecision": "float16"})`.
--
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]
