feat: add mm embedding model and its factory. #471
+153
−0
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
dongxianzhe
requested review from
liutongxuan,
wly-115,
xiao-yu-chen and
yq33victor
| const ModelInputParams& input_params) = 0; | ||
|
|
||
| virtual torch::Tensor logits(const torch::Tensor& hidden_states, | ||
| const torch::Tensor& seleted_idxes) { |
Collaborator
There was a problem hiding this comment.
is seleted_idxes a spelling mistake issue? selected_idxes?
Collaborator
Author
There was a problem hiding this comment.
I've fixed seleted_idxes to selected_idxes.
yq33victor
reviewed
Dec 3, 2025
| virtual std::vector<torch::Tensor> encode( | ||
| const ModelInputParams& input_params) = 0; | ||
|
|
||
| virtual torch::Tensor logits(const torch::Tensor& hidden_states, |
Collaborator
There was a problem hiding this comment.
no need to define these interface in MMEmbeddingVLM, move these to MMEmbeddingVLMImpl
Collaborator
Author
There was a problem hiding this comment.
Done. Moved the empty implementation from MMEmbeddingVLM to MMEmbeddingVLMImpl.
| } | ||
|
|
||
| MMEmbeddingVLMFactory ModelRegistry::get_mm_embedding_vlm_factory( | ||
| const std::string& name) { |
Collaborator
There was a problem hiding this comment.
nit: maybe need yo rename :(
register_vlm_mm_embedding_factory ----> vlm_mm_embedding
and
get_mm_embedding_vlm_factory ----> mm_embedding_vlm
Collaborator
Author
There was a problem hiding this comment.
Done. Rename register_vlm_mm_embedding_factory to register_mm_embedding_vlm_factory.
…mpl and fix some function name.
yq33victor
approved these changes
Dec 8, 2025
Collaborator
|
LGTM |
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.
Add an MMEmbeddingVLM interface for the encode service that loads only the vision model.