fix: _get_num_multimodal_tokens video branch (#43329) #43330
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
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: ernie4_5_vl_moe, glm46v, glm4v, qwen2_5_vl, qwen2_vl, qwen3_vl, video_llama_3 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
What does this PR do?
Fixes #43329
Summary
_get_num_multimodal_tokens(video_sizes=...)crashed in multiple multimodal processors because thevideo branch called
self.video_processor.get_number_of_video_patches(...)(not implemented on several videoprocessors), and used
merge_sizewithout initializing it (it was only set in the image branch).This meant CI never exercised the video route (tests only covered
image_sizes).Changes
self.video_processor.merge_size).
alias to the existing helper or as a small utility consistent with preprocessing).
branch is exercised in CI.
Affected processors
Relevant Tests
python -m pytest -q
tests/models/qwen2_vl/test_processing_qwen2_vl.py::Qwen2VLProcessorTest::test_get_num_vision_tokens
tests/models/qwen2_5_vl/
test_processing_qwen2_5_vl.py::Qwen2_5_VLProcessorTest::test_get_num_vision_tokens
tests/models/qwen3_vl/test_processing_qwen3_vl.py::Qwen3VLProcessorTest::test_get_num_vision_tokens
tests/models/video_llama_3/
test_processing_video_llama_3.py::VideoLlama3ProcessorTest::test_get_num_vision_tokens
tests/models/ernie4_5_vl_moe/
test_processing_ernie4_5_vl_moe.py::Ernie4_5_VL_MoeProcessorTest::test_get_num_vision_tokens
tests/models/glm4v/test_processor_glm4v.py::Glm4vProcessorTest::test_get_num_vision_tokens_video
tests/models/glm46v/test_processor_glm46v.py::Glm46VProcessorTest::test_get_num_vision_tokens_video