mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 31 Packages Projects Releases Wiki Activity

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
9 changed files with 167 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/models/models.h
+5
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;