Fix broken Min/Max Tracking Across Calibration Batches#2705
Open
Ebraheem1 wants to merge 2 commits into
Open
Conversation
TobyRoseman
requested changes
May 21, 2026
Collaborator
TobyRoseman
left a comment
TobyRoseman
left a comment
There was a problem hiding this comment.
Please write unit tests that fail without your fix and pass with your fix. Also avoid writing your unit tests directly against underscore/private method.
Author
|
I only included breaking tests without the modifications. |
Author
|
@TobyRoseman do you have other comments here? |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixed Bug
When you run activation quantization with multi-batch calibration, the min/max are picked from the last batch's tensor. This is a faulty behavior that produces wrong quantization ranges.
Tests
coremltools/test/optimize/test_utils.pyandcoremltools/optimize/coreml/experimental/test_post_training_quantization.py.Issue
Fixes #2704