Add multimodal support to optimum-executorch #116
Closed
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
This commit adds comprehensive support for image-text-to-text models to optimum-executorch, extending the existing recipe system to handle multimodal vision-language models. Key changes: - Added new image-text-to-text task to task registry - Created ImageTextToTextExportableModule for multimodal model export - Extended integrations to support both vision encoder and text decoder export - Added comprehensive tests for multimodal functionality - CLI now supports --task image-text-to-text for multimodal models This enables users to export models like Gemma-3, LLaVA, and other vision-language models using the familiar optimum-executorch workflow: optimum-cli export executorch --model google/gemma-3-4b-it --task image-text-to-text --recipe xnnpack
mergennachin
force-pushed
the
add-multimodal-support
branch
from
d99a0eb to
276c188
Compare
|
Is it overlap with #111? |
|
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. |
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Outdated suggestions cannot be applied.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.
This commit adds comprehensive support for image-text-to-text models to optimum-executorch, extending the existing recipe system to handle multimodal vision-language models.
Key changes:
This enables users to export models like Gemma-3, LLaVA, and other vision-language models using the familiar optimum-executorch workflow:
optimum-cli export executorch --model google/gemma-3-4b-it --task image-text-to-text --recipe xnnpack