nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 25 Packages Projects Releases Wiki Activity

mtmd: support "frame merge" for qwen-vl-based models (#21858)

Browse Source 
* feat: add video support for Qwen3.5

* various clean up

* revise the design

* fix llava-uhd case

* nits

* nits 2

---------

Co-authored-by: andrewmd5 <1297077+andrewmd5@users.noreply.github.com>
This commit is contained in:
Xuan-Son Nguyen
2026-06-06 21:17:25 +02:00
committed by GitHub
co-authored by andrewmd5
parent 6b80c74f28
commit 31e82494c0
10 changed files with 197 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/models/models.h
+3 -2
View File
@@ -31,10 +31,11 @@ struct clip_graph_pixtral : clip_graph {
struct clip_graph_qwen2vl : clip_graph {
clip_graph_qwen2vl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;
ggml_tensor * build_inp_with_temporal_merge();
};
struct clip_graph_qwen3vl : clip_graph {
clip_graph_qwen3vl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
struct clip_graph_qwen3vl : clip_graph_qwen2vl {
clip_graph_qwen3vl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph_qwen2vl(ctx, img) {}
ggml_cgraph * build() override;
};