mtmd: dsocr-tiles test fixes - #25486
Merged
ngxson merged 1 commit intoJul 10, 2026
Merged
Conversation
…pt space; make DRY opt-in and n_predict model-specific
Contributor
Author
|
The reg-test gate/tolerance is relaxed because testing with the HF ref on CPU and CUDA (and a modified HF ref on Metal/mps) showed the baseline should be set higher, and the tolerance should be wider when considering different weight dtypes and backends. This is all verified and reproducible: https://github.com/sfallah/llama-mtmd-eval |
github-actions
Bot
added
the
mtmd
ngxson
added a commit
that referenced
this pull request
Jul 10, 2026
* mtmd: deepseek-ocr v1 multi-tile dynamic resolution + unified image-preprocessors for both versions (ds-ocr v1 and v2) * remove hacky API * fuse row into a long image * almost working * adapt to new preprocessor api * rm debugging printf * improve * mtmd: dsocr-tiles fixes (#25481) * ds-ocr img-preproc fuse_row tile-drop fix for multi rows and columns images * mtmd drop the duplicate redundant img_end * deepseekocr graph simplify CLS broadcast cleanup * test-deepseek-ocr: relax v1 single-view tolerance; drop trailing prompt space; make DRY opt-in and n_predict model-specific (#25486) --------- Co-authored-by: Saba Fallah <10401143+sfallah@users.noreply.github.com> Co-authored-by: Saba Fallah <sabafallah@gmail.com>
satindergrewal
pushed a commit
to satindergrewal/llama.cpp
that referenced
this pull request
Aug 12, 2026
* mtmd: deepseek-ocr v1 multi-tile dynamic resolution + unified image-preprocessors for both versions (ds-ocr v1 and v2) * remove hacky API * fuse row into a long image * almost working * adapt to new preprocessor api * rm debugging printf * improve * mtmd: dsocr-tiles fixes (ggml-org#25481) * ds-ocr img-preproc fuse_row tile-drop fix for multi rows and columns images * mtmd drop the duplicate redundant img_end * deepseekocr graph simplify CLS broadcast cleanup * test-deepseek-ocr: relax v1 single-view tolerance; drop trailing prompt space; make DRY opt-in and n_predict model-specific (ggml-org#25486) --------- Co-authored-by: Saba Fallah <10401143+sfallah@users.noreply.github.com> Co-authored-by: Saba Fallah <sabafallah@gmail.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
AI usage disclosure: YES - I used AI assistance for code review, debugging, implementation checks, and testing. I have reviewed the submitted changes and take responsibility for the full contents of this PR.