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/clip-model.h

@@ -542,6 +542,11 @@ struct clip_model {
     int32_t n_sam_layers = 12; // used by deepseek-ocr sam encoder
 
     std::vector<clip_layer> sam_layers;
+
+    // deepseek-ocr-2
+    ggml_tensor * resample_query_768 = nullptr;
+    ggml_tensor * resample_query_1024 = nullptr;
+
     // lfm2 audio
     std::array<ggml_tensor *, 7> pre_encode_conv_X_w = {nullptr};
     std::array<ggml_tensor *, 7> pre_encode_conv_X_b = {nullptr};