masahi edited a comment on pull request #9873: URL: https://github.com/apache/tvm/pull/9873#issuecomment-1015850768
> Also, remove support for non-float16 tensorcore operations as they cause large degradation in accuracy Yeah, I also noticed this implicit downcasting before, I'm in favor of this change. Users can always explicitly cast their inputs to fp16. The original code was added before we have the fp16 conversion pass. This may break existing flows if some users depend on this behavior, which is also the default in cudnn/cublas. Personally I don't mind it, but if that's concerning we can always add a workaround to allow the old behavior. -- 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]
