[ntuple] some fixes to Real32Quant #17252
Merged
Conversation
This file contains 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
- fix wrong calculation for maxErr in ntuple_packing - fix wrong emin/emax adjustment in UnquantizeReals - ensure min and max values of ValueRange are normal
Thanks, confirmed on |
jblomer
approved these changes
Dec 11, 2024
Test Results 17 files 17 suites 3d 22h 50m 42s ⏱️ For more details on these failures, see this check. Results for commit 71b5758. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Notes
This should fix an assertion failure observed on AArch64 by @hahnjo.
These bugs do not have the potential of generating corrupted data (barring users that pass exotic floats as min/max values), but they can trigger false positives of the "out of range" assertion failures.
Checklist: