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

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 <redacted>
* fix the \r\n mess

* add width and heads to MmprojModel.set_gguf_parameters

---------

Co-authored-by: Sigbjørn Skjæret <redacted>