Hi there,
We are playing with ahead of time compilation (AOTInductor), to be able to produce models that can be executed by a C++ program ; we’ve seen great results, but results seems even better when the ‘cuda-graph’ options are used, however that doesn’t seem to work with inductor which is the default value used with AOT.
Is there a fundamental reason this cannot work, or is there hope it can with some work ?
Thanks !