fix: forward use_cache kwarg to attention mixer in nemotron_h#45792
Merged
zucchini-nlp merged 2 commits intoMay 5, 2026
Conversation
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: nemotron_h |
zucchini-nlp
approved these changes
May 5, 2026
77148a6 to
a03e2ed
Compare
|
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. |
Exile333
pushed a commit
to Exile333/transformers
that referenced
this pull request
May 6, 2026
…gface#45792) * fix: forward use_cache kwarg to attention mixer in nemotron_h * Ran make fix-repo
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In
src/transformers/models/nemotron_h/modular_nemotron_h.py:294the attention mixer is called withuser_cache=use_cache. The typo meansuse_cacheis never forwarded and an unexpecteduser_cachekwarg gets passed through instead.Simply, Rename the keyword argument from
user_cachetouse_cacheso the flag actually reaches the attention mixer.