ibsidorenko opened a new pull request, #11210: URL: https://github.com/apache/tvm/pull/11210
This PR is an attempt to revive [PR#9164](https://github.com/apache/tvm/pull/9164) . It enables folding of constants for QNN operations. Motivation to have this feature is BYOC use cases. One important thing: for the case when we call `FoldConstant` before `FakeQuantizationToInteger` pass, we can prevent FQ2I from converting some ops to qnn equivalent. To avoid this, callback argument was added in `FoldConstant` pass that allows to skip expressions from folding. Co-authored-by: Alexander Peskov <[email protected]> -- 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]
