[WIP] debug regression in mul operator with 'big' dimensions - post tract 0.21.5 #1497
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
JulienBalianSonos
changed the title
|
As discussed, this bug was introduced in the |
|
I confirm after testing: the new PR fixes the issue. |
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Outdated suggestions cannot be applied.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.
Regression appeared after tract v0.21.5.
Simple mul operator between an input and a "variable" tensor fail when specific dimensions implied.
Original failing test is with shapes:
we manage to reduce the the problem to
But not further (reducing any dim from here allow exact results).
The problem is not sensible to the values in input tensor, nor parameter,
This is likely a multiplication layout issue.