mtmd: Add DeepSeekOCR 2 Support (#20975)

* mtmd: DeepSeek-OCR 2 support, with multi-tile dynamic resolution

* introduced clip_image_f32::add_viewsep

* address PR review

- drop redundant ggml_cpy ops in both deepseekocr versions build
- drop no-op ggml_cont in build_sam
- assert num_image_tokens deepseekocr2
- view_seperator as (1, n_embd) at conversion (for both versions)
- drop redundant ggml_reshape_2d

* Update tools/mtmd/models/deepseekocr2.cpp

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>

---------

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>

tools/mtmd/mtmd-image.h

@@ -144,6 +144,26 @@ struct mtmd_image_preprocessor_deepseekocr : mtmd_image_preprocessor {
     bool preprocess(const clip_image_u8 & img, clip_image_f32_batch & output) override;
 };
 
+// DeepSeek-OCR-2: a 1024x1024 global view, plus InternVL-style 768x768 local
+// tiles when the image is larger than a tile in either dimension.
+struct mtmd_image_preprocessor_deepseekocr2 : mtmd_image_preprocessor {
+    static constexpr int base_size = 1024; // global view
+    static constexpr int tile_size = 768;  // local tile
+    static constexpr int min_tiles = 2;
+    static constexpr int max_tiles = 6;
+
+    mtmd_image_preprocessor_deepseekocr2(const clip_ctx * ctx) : mtmd_image_preprocessor(ctx) {}
+    bool preprocess(const clip_image_u8 & img, clip_image_f32_batch & output) override;
+
+private:
+    static std::vector<clip_image_size> get_target_ratios();
+    static clip_image_size              find_closest_aspect_ratio(
+        float                                aspect_ratio,
+        const std::vector<clip_image_size> & target_ratios,
+        int                                  width,
+        int                                  height);
+};
+
 // custom image preprocessing for Step3VL
 // ref: https://huggingface.co/stepfun-ai/Step3-VL-10B/blob/main/processing_step3.py
 struct mtmd_image_preprocessor_step3vl : mtmd_image_preprocessor_llava_uhd {