model : support step3-vl-10b (#21287)

* feat: support step3-vl-10b

* use fused QKV && mapping tensor in tensor_mapping.py

* guard hardcoded params and drop crop metadata

* get understand_projector_stride from global config

* img_u8_resize_bilinear_to_f32 move in step3vl class

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fix the \r\n mess

* add width and heads to MmprojModel.set_gguf_parameters

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

tools/mtmd/CMakeLists.txt

@@ -31,6 +31,7 @@ add_library(mtmd
             models/pixtral.cpp
             models/qwen2vl.cpp
             models/qwen3vl.cpp
+            models/step3vl.cpp
             models/siglip.cpp
             models/whisper-enc.cpp
             models/deepseekocr.cpp