Add dotsocr #2077
Open
Add dotsocr #2077
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
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
tianyuan211
requested review from
afierka-intel,
kzawora-intel,
madamczyk-intel,
mgawarkiewicz-intel,
michalkuligowski,
vivekgoe and
xuechendi
as code owners
tianyuan211
requested review from
PatrykWo,
jikunshang and
mswiniarsk
as code owners
Signed-off-by: tianyuan211 <[email protected]>
Signed-off-by: tianyuan211 <[email protected]>
czhu15
reviewed
Oct 27, 2025
| changed = True | ||
| new_dict[k] = v | ||
| if changed: | ||
| # skip read-only attributes |
There was a problem hiding this comment.
not sure if this is the correct behavior, + @yangulei for comment.
There was a problem hiding this comment.
What attributes of dots.ocr will cause issue here?
There was a problem hiding this comment.
What attributes of dots.ocr will cause issue here?
the error is AttributeError: can't set attribute 'dummy_inputs'
Signed-off-by: tianyuan211 <[email protected]>
fixed |
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.
Summary
This PR adds support for integrating DotsOCR into vLLM, enabling end-to-end document OCR and layout parsing through the multimodal inference pipeline.
Changes
vllm/model_executor/models/dots_ocr.py.compute_logits,forward, and multimodal embedding fusion for OCR-specific tasks.Motivation
DotsOCR integration allows vLLM to run lightweight, high-accuracy OCR and document layout understanding tasks without requiring server-based inference.
Test
python3 examples/offline_inference/vision_language.py -m 'dots_ocr'