FrozenGene commented on pull request #9735:
URL: https://github.com/apache/tvm/pull/9735#issuecomment-1007990697
> > @AndrewZhaoLuo Sorry for later reply. Does this help us to solve ADT
problem in our MixedPrecision? Let us imagine we have one `if` node in our
relay graph, `if` will be converted two subgraphs mentioned by you in this pr.
For example:
> > ```python
> > fn main():
> > let %1 = xxx;
> > let %2 = if (%1) {
> > let %3: = @func___inference_a(%4, %5, %6)
> > } else {
> > let %7: = @func___inference_b(%8, %9)
> > };
> > ```
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> > Then we have two subgraph `func___inference_a` and `func___inference_b`.
Does this help us to make our two subgraph type infer correctly? As I see you
have supported `GlobalVarNode`.
>
> @FrozenGene not sure if I understand the concern 😅, global var nodes are
just used to reference function calls right? These functions have a known type
ahead of time right?
@AndrewZhaoLuo Yes. In fact I saw your pr support global var node, I thought
you will leverage it to solve this undo:
https://github.com/apache/tvm/blob/main/src/relay/transforms/to_mixed_precision.cc#L297
--
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]
