Restrict scale's values of dequantizeLinear and quantizeLinear to be positive and nonzero #906
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
philloooo
reviewed
Nov 25, 2025
BruceDai
changed the title
fdwr
approved these changes
Jan 16, 2026
Collaborator
fdwr
left a comment
fdwr
left a comment
There was a problem hiding this comment.
👍
(awaiting Phillis and Reilly before merging?)
reillyeon
suggested changes
Jan 20, 2026
| **Arguments:** | ||
| - <dfn>input</dfn>: an {{MLOperand}}. The input tensor. | ||
| - <dfn>scale</dfn>: an {{MLOperand}}. The scale tensor to multiply each input value by after adjusting by the zero point. It must be [=blockwise broadcastable=] with the input. | ||
| - <dfn>scale</dfn>: an {{MLOperand}}. The scale tensor to multiply each input value by after adjusting by the zero point. It must be [=blockwise broadcastable=] with the input. Values must be positive and nonzero, or else behaviors are implementation dependent (e.g. correct results, incorrect results, compilation failure). |
Member
There was a problem hiding this comment.
Use the phrase "implementation-defined".
Suggested change
| - <dfn>scale</dfn>: an {{MLOperand}}. The scale tensor to multiply each input value by after adjusting by the zero point. It must be [=blockwise broadcastable=] with the input. Values must be positive and nonzero, or else behaviors are implementation dependent (e.g. correct results, incorrect results, compilation failure). | |
| - <dfn>scale</dfn>: an {{MLOperand}}. The scale tensor to multiply each input value by after adjusting by the zero point. It must be [=blockwise broadcastable=] with the input. Values must be positive and nonzero, or else the behavior is [=implementation-defined=] (e.g. correct results, incorrect results or compilation failure). |
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.
This is a Spec change PR for #879 where we're discussing about the lack of widespread support for the current negative scale of
dequantizeLinearandquantizeLinearacross all backend.@fdwr @reillyeon @huningxin PTAL, thanks!
Preview | Diff