mtmd: (WIP) gemma3n vision support #17961
Draft
+1,492
−5
Conversation
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
1 participant
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Outdated suggestions cannot be applied.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.
This is a non-working WIP of gemma 3n vision implement in ggml. Commits are from June 2025 because it was under NDA before the model released.
I could not finished it on-time because testing was tricky and there was no native
transformersimplementation. My code was heavily based on mlx-vlm implementation: https://github.com/Blaizzy/mlx-vlm/blob/main/mlx_vlm/models/gemma3n/vision.pyIMPORTANT INFO: I am NOT actively working on this feature, but only pushing the PR for visibility. Contributors can take over this task if needed.