nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 18 Packages Projects Releases Wiki Activity

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

Browse Source 
* 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>
This commit is contained in:
forforever73
2026-04-08 09:51:31 +02:00
committed by GitHub
co-authored by Sigbjørn Skjæret
parent 97508acb17
commit 09343c0198
12 changed files with 537 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/models/models.h
+5
View File
@@ -33,6 +33,11 @@ struct clip_graph_qwen3vl : clip_graph {
ggml_cgraph * build() override;
};
struct clip_graph_step3vl : clip_graph {
clip_graph_step3vl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;
};
struct clip_graph_youtuvl : clip_graph {
clip_graph_youtuvl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;