Add a dim check mechanism in Transpose and fix qwen3_vl_moe weight mapping#44037
Merged
Cyrilvallez merged 6 commits intomainfrom Feb 16, 2026
Merged
Add a dim check mechanism in Transpose and fix qwen3_vl_moe weight mapping#44037Cyrilvallez merged 6 commits intomainfrom
Cyrilvallez merged 6 commits intomainfrom
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
ArthurZucker
approved these changes
Feb 16, 2026
| # In this case, check the shapes before transposing | ||
| else: | ||
| # NOTE: this rely on the first param name, so cannot be used for many-to-one operation | ||
| expected_shape = kwargs["model"].get_parameter(kwargs["full_layer_name"]).shape |
Collaborator
There was a problem hiding this comment.
good, we should probably make the TP op overwrite the shape ? or actually the shape you check is never TPed?
Member
Author
There was a problem hiding this comment.
TP is still not defined for only a Transpose anyway... IMO we should wait for support before taking a decision on this
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: qwen3_vl_moe |
Cyrilvallez
changed the title
This was referenced Feb 16, 2026
4 tasks
aman-coder03
pushed a commit
to aman-coder03/transformers
that referenced
this pull request
Feb 17, 2026
…pping (huggingface#44037) * start * test * betetr * fix * change name * cannot revert
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
As per the title. Supersedes #43913