-
-
Notifications
You must be signed in to change notification settings - Fork 4.9k
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] Refactor model executable interface for multimodal models #10570
Conversation
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
👋 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: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
This PR is mostly done but with a few caveats:
All the other models included in this PR have been tested with example scripts to ensure v0 compatibility. Full v1 compatibility will be worked in the next PR. |
I'm getting this error for internvl tests (
I think it's because |
This pull request has merge conflicts that must be resolved before it can be |
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
I pushed a change which I think should be a clean fix for this. Let me know what you think! |
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
…project#10570) Signed-off-by: Roger Wang <[email protected]> Signed-off-by: Andrew Feldman <[email protected]>
…project#10570) Signed-off-by: Roger Wang <[email protected]>
This PR refactors the interface of all multimodal language models for V1 VLM re-arch and
torch.compile
support. In particular, all multimodal model implementations on vLLM will need to meet the following requirements:get_multimodal_embeddings(**kwargs)
implemented inXYZModel
orXYZForConditionalGeneration
get_input_embeddings(input_ids, multimodal_embeddings)
implemented inXYZModel
orXYZForConditionalGeneration
to output input embeddings to be passed to the language backbone.XYZModel
orXYZForConditionalGeneration
until V0 is fully deprecated.List of LMMs to be worked on
This PR is a prerequisite of applying #9871 to all multimodal models on vLLM.