Register Reduction OPs, eager mode, forward pass #1228
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jmalone-tt
reviewed
Oct 9, 2025
|
|
||
| namespace tt_eager::ext { | ||
|
|
||
| inline std::optional<std::variant<int, ttnn::SmallVector<int>>> to_ttnn_dim_variant( |
Collaborator
There was a problem hiding this comment.
Is there a reason this function is kept here and not in eager_common.hpp?
| break; | ||
| } | ||
| } | ||
| TORCH_CHECK(pos >= 0, "Dimname not found in tensor"); |
Collaborator
There was a problem hiding this comment.
Looks like we have several instances of TORCH_CHECK that all return "Dimname not found in tensor" on failure - can we make this more descriptive / potentially disambiguate the messages so it is easier to debug for users
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Registering Reduction TTNN OPs (PR on top of #1210)
Problem description
Existing TTNN OPs should be registered to Pytorch Dispatcher.
The scope of this PR is Reduction OPs only, other groups of OPs are planned to be added in other PRs
What's changed
Reduction wrappers are introduced, Reduction TTNN OPs are registered
TODO: