Konstantin Arturov
Konstantin Arturov
@jgong5, at this point our main concern (and hence the RFC) is not how to improve performance of models with truly dynamic shapes (e.g. Hifagan on ATS-M), but how not...
> If these dynamic hints for individual dims are passed as hints, you have the flexibility to choose the algorithms you like That adds complexity at our side, but is...
>Based on this recommendation it looks like there is a misunderstanding here. As far as I understand, in the graph mode the framework knows what dimensions are static and what...
As this PR affects performance, and OpenVINO team didn't complain about this issue after their testing, let's not merge it until perf CI is back and confirms no regressions.