thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

mtmd : Add Nemotron Nano 12B v2 VL support (#19547)

Browse source 
* nemotron nano v2 vlm support added

* simplified code; addressed reviews

* pre-downsample position embeddings during GGUF conversion for fixed input size
This commit is contained in:
Anav Prasad 2026-02-14 05:07:00 -08:00 • committed by GitHub
parent 1725e316c1
commit 01d8eaa28d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 167 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
tools/mtmd/models/models.h
View file

@ -42,6 +42,11 @@ struct clip_graph_internvl : clip_graph {
ggml_cgraph * build() override;
};
struct clip_graph_nemotron_v2_vl : clip_graph {
clip_graph_nemotron_v2_vl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;
};
struct clip_graph_llama4 : clip_graph {
clip_graph_llama4(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;