sleepy/llama.cpp
1
0
Fork 0
Code Issues 16 Pull Requests Actions 139 Packages Projects Releases Wiki Activity

mtmd: qwen3 audio support (qwen3-omni and qwen3-asr) (#19441)

Browse Source 
* add qwen3a

* wip

* vision ok

* no more deepstack for audio

* convert ASR model ok

* qwen3 asr working

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* nits

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fix bad merge

* fix multi inheritance

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Xuan-Son Nguyen
2026-04-12 23:57:25 +02:00
committed by GitHub
parent 1e9d771e2c
commit 21a4933042
10 changed files with 301 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/models/models.h
+5
View File
@@ -152,6 +152,11 @@ struct clip_graph_mobilenetv5 : clip_graph {
const mobilenetv5_block & block);
};
struct clip_graph_qwen3a : clip_graph {
clip_graph_qwen3a(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;
};
struct clip_graph_kimik25 : clip_graph {
clip_graph_kimik25(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;