-
-
Notifications
You must be signed in to change notification settings - Fork 5.8k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[V1] Fix multimodal profiling for Molmo
#11325
[V1] Fix multimodal profiling for Molmo
#11325
Conversation
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can do one of these:
🚀 |
Signed-off-by: ywang96 <ywang@example.com>
Signed-off-by: ywang96 <ywang@example.com> Co-authored-by: ywang96 <ywang@example.com>
Signed-off-by: ywang96 <ywang@example.com> Co-authored-by: ywang96 <ywang@example.com>
Signed-off-by: ywang96 <ywang@example.com> Co-authored-by: ywang96 <ywang@example.com>
Signed-off-by: ywang96 <ywang@example.com> Co-authored-by: ywang96 <ywang@example.com> Signed-off-by: Bowen Wang <abmfy@icloud.com>
Signed-off-by: ywang96 <ywang@example.com> Co-authored-by: ywang96 <ywang@example.com>
Molmo is a special case where the input processing also handles the preprocessing of multimodal data, therefore the dummy data for this model is defined as
MultiModalKwags
without aPIL.Image
.This PR adds a temporary workaround to fix this issue as well as renaming some functions to indicate their purposes better.