Adding some additional discussion with @csullivan .
We agree that:
- There are different ways to encode layout and padding decisions:
- E0: BufferConstraint(as element in the IR)
- E1: Composing a stage that transforms the layout(a loop that represents
the mapping)
- Non-local rewrites ar
Hi Mark, thank you for clarifying.
If I'm not interested in using the virtual_device feature, is there a way to
disable it? The issue is that without the patch above, it is not possible to
use any pass that is based on the ExprMutator in Python, because the TE
Compiler complains with the abov
Yes, I'd very much support a patch to get you going again. I'm confused as to
why just setting the virtual_device_ in the visitor directly does not work, so
option a is you send me a unit test and I dig into that. Option b is your
patch, however since you've needed to bounce back to c++ perhap
As discussed in
https://github.com/apache/tvm-rfcs/blob/main/rfcs/0067-quarterly-releases.md,
we will be publishing a release of TVM on mid July. We will do a branch cut
soon but accept cherry-picked changes for a couple weeks. See the [release
steps](https://github.com/apache/tvm-rfcs/blob/mai
Merged #75 into main.
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/75#event-6816322214
You are receiving this because you are subscribed to this thread.
Message ID:
thanks @alter-xp, the PR is now merged! please open an RFC tracking issue and
list out the PRs we can expect there, then we can proceed on the CI changes.
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/75#issuecomment-1156983012
You are receiving th
@areusch [a tracking issue](https://github.com/apache/tvm/issues/11506) is
ready. I will keep updating it.
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/75#issuecomment-1157154054
You are receiving this because you are subscribed to this thread.
