Adding Multi Resolution Changes for Gemma4 Model - #1244
Open
tchawada wants to merge 4 commits into
Open
Conversation
Signed-off-by: Tanisha Chawada <tchawada@qti.qualcomm.com>
Signed-off-by: Tanisha Chawada <tchawada@qti.qualcomm.com>
mohiso22
reviewed
Aug 6, 2026
| vision_size = user_vision_size | ||
| else: | ||
| vision_size = self._get_mm_tokens_per_image() | ||
| if height is None or width is None: |
Contributor
There was a problem hiding this comment.
This user_vision_size warning is necessary,
Signed-off-by: Tanisha Chawada <tchawada@qti.qualcomm.com>
Signed-off-by: Tanisha Chawada <tchawada@qti.qualcomm.com>
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds multi-resolution Gemma4 vision workflow support via a new example script:
gemma4_multi_resolution.py.
The script compiles a single Gemma4 setup with multiple (height, width) specializations, then runs
generation across those resolutions by dynamically selecting the required vision token budget
(choose_gemma4_max_soft_tokens). This demonstrates
end-to-end compile + generate for variable image sizes without per-resolution recompilation.