ggml-org/llama.cpp b8705

on GitHub

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