Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Validate no duplicate axes for reduction ops #683

Merged

Conversation

inexorabletash
Copy link
Contributor

@inexorabletash inexorabletash commented May 9, 2024

Suggested behavior matches the Chromium prototype implementation.

Fixes #681


Preview | Diff

Suggested behavior matches the Chromium prototype implementation.

Fixes webmachinelearning#681
@inexorabletash
Copy link
Contributor Author

Seems pretty straightforward. Please take a look @fdwr and @huningxin ?

Copy link
Collaborator

@fdwr fdwr left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

One comment, else LGTM. TY JB.

index.bs Outdated Show resolved Hide resolved
inexorabletash and others added 3 commits May 10, 2024 08:56
Nop reductions are valid (where axes are empty)

Co-authored-by: Dwayne Robinson <dwayner@microsoft.com>
Copy link
Collaborator

@fdwr fdwr left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍

@inexorabletash inexorabletash changed the title Validate axes and input rank for reduction ops Validate axes for reduction ops May 10, 2024
@inexorabletash inexorabletash changed the title Validate axes for reduction ops Validate no duplicate axes for reduction ops May 10, 2024
index.bs Outdated Show resolved Hide resolved
@inexorabletash
Copy link
Contributor Author

@huningxin can you please review the latest update, and merge if it looks good? thanks!

Copy link
Contributor

@huningxin huningxin left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, thanks!

@huningxin huningxin merged commit 5d94426 into webmachinelearning:main May 14, 2024
2 checks passed
github-actions bot added a commit that referenced this pull request May 14, 2024
SHA: 5d94426
Reason: push, by huningxin

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@inexorabletash inexorabletash deleted the validate-reduction-axes-rank branch May 14, 2024 17:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Shall we update the spec to add constraints on the axes and the input rank for the reduction operator?
3 participants