Add rankRange to opSupportLimits()#828
Merged
fdwr merged 6 commits intowebmachinelearning:mainfrom Apr 9, 2025
inexorabletash:tensor-limits
Merged
Add rankRange to opSupportLimits()#828fdwr merged 6 commits intowebmachinelearning:mainfrom inexorabletash:tensor-limits
fdwr merged 6 commits intowebmachinelearning:mainfrom
inexorabletash:tensor-limits
Conversation
Add rankRange to opSupportLimits() by renaming MLSupportLimits to MLDataTypeLimits (still used for inputs, constants, and output operands), and deriving MLTensorLimits (used for tensor operands) which adds the new member as a MLRankRange dictionary. This also adds a note about an operand's allowed data types and ranks, indicating the implementations may extend or impose limits. Finally, maxTensorByteLength is exposed at the top level of the dictionary.
reillyeon
reviewed
Mar 15, 2025
Contributor
Author
|
Ready for review, I think. Please take a look? |
fdwr
reviewed
Mar 17, 2025
Collaborator
fdwr
left a comment
fdwr
left a comment
There was a problem hiding this comment.
A few thoughts good sir. 🔍
Contributor
Author
|
Thanks @fdwr ! This should still match the Chromium implementation at least as far as what's web-observable, even if the IDL differs somewhat. The discussion around whether or how to represent output tensors is still unresolved; two options:
Preferences? |
Collaborator
Incremental progress? |
Contributor
Author
|
I opened #835 to capture the output tensor discussion. So... good to merge this as-is? |
github-actions bot
added a commit
that referenced
this pull request
Apr 9, 2025
SHA: 963437c Reason: push, by fdwr Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
fdwr
reviewed
Apr 9, 2025
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
Add rankRange to opSupportLimits() by renaming MLSupportLimits to MLDataTypeLimits (still used for inputs, constants, and output operands), and deriving MLTensorLimits (used for tensor operands) which adds the new member as a MLRankRange dictionary.
This also adds a note about an operand's allowed data types and ranks, indicating the implementations may extend or impose limits.
In addition, maxTensorByteLength is added to the MLOpSupportLimits dictionary.
Based on the work in Chromium by Reilly Grant, Wei Wang, and Junwei Fu.
Resolves #456
Preview | Diff