]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
mtmd : DeepSeek-OCR image processing fixes, img_tool::resize padding refactor (#23345)
authorSaba Fallah <redacted>
Wed, 20 May 2026 15:37:10 +0000 (17:37 +0200)
committerGitHub <redacted>
Wed, 20 May 2026 15:37:10 +0000 (17:37 +0200)
commita8681a0ed2e3f2a7452e642639671bcec20b865c
tree84778831364920fc0b89390143f06c3f8dd956d2
parentacd604fb277044e07c2bff01f4c169167b45f478
mtmd : DeepSeek-OCR image processing fixes, img_tool::resize padding refactor (#23345)

* mtmd : deepseek-ocr fixes, improvements and refactoring

- image processing changes to achieve full parity with Pillow (reference impl)
- SAM mask casting only when flash-attn is on
- SAM refactor (build_sam() extracted so deepseek-ocr-2 can reuse it)
- llama-chat changes to fix server/WebUI issue (new media_markers_first())
- adapted test-chat-template and added test cases for deepseek-ocr
- changed regression test for deepseek-ocr to use CER+chrF scores for ground-truth comparison; removed embedding-model
- ty.toml ignore unresolved-import for tools/mtmd/tests/**

* image-text reordering fix removed

* refactor bool add_padding + pad_rounding enum into a single pad_style enum
tools/mtmd/clip-model.h
tools/mtmd/clip.cpp
tools/mtmd/models/deepseekocr.cpp
tools/mtmd/models/models.h
tools/mtmd/mtmd-image.cpp
tools/mtmd/tests/test-1-extracted.md [deleted file]
tools/mtmd/tests/test-1-extracted.txt [deleted file]
tools/mtmd/tests/test-1-ground-truth.txt [new file with mode: 0644]
tools/mtmd/tests/test-deepseek-ocr.py
tools/mtmd/tests/tests-requirements.txt
ty.toml