Skip to content

Fix type hint for attention_chunk_size in Llama4TextConfig#45002

Merged
ArthurZucker merged 1 commit intohuggingface:mainfrom
hmellor:llama4-type-hint
Mar 25, 2026
Merged

Fix type hint for attention_chunk_size in Llama4TextConfig#45002
ArthurZucker merged 1 commit intohuggingface:mainfrom
hmellor:llama4-type-hint

Conversation

@hmellor
Copy link
Member

@hmellor hmellor commented Mar 25, 2026

None is a valid value that can be used to disable chunked attention in DynamicCache and Flex Attention.

hf.co/morgendave/EAGLE-Llama-4-Scout-17B-16E-Instruct is an example of a checkpoint which does this.

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
@github-actions
Copy link
Contributor

[For maintainers] Suggested jobs to run (before merge)

run-slow: llama4

@HuggingFaceDocBuilderDev

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.

@github-actions
Copy link
Contributor

View the CircleCI Test Summary for this PR:

https://huggingface.co/spaces/transformers-community/circle-ci-viz?pr=45002&sha=fba53e

Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yep ty

@ArthurZucker ArthurZucker merged commit c9faacd into huggingface:main Mar 25, 2026
27 of 29 checks passed
@hmellor hmellor deleted the llama4-type-hint branch March 25, 2026 20:42
zucchini-nlp pushed a commit to zucchini-nlp/transformers that referenced this pull request Mar 27, 2026
…ngface#45002)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants