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

* 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
co-authored by Sigbjørn Skjæret
parent 1e9d771e2c
commit 21a4933042
10 changed files with 301 additions and 21 deletions
+10
View File
@@ -413,10 +413,20 @@ struct clip_model {
ggml_tensor * conv1d_1_b = nullptr;
ggml_tensor * conv1d_2_w = nullptr;
ggml_tensor * conv1d_2_b = nullptr;
ggml_tensor * conv_out_w = nullptr;
ggml_tensor * conv_out_b = nullptr;
ggml_tensor * mm_norm_pre_w = nullptr;
ggml_tensor * mm_norm_pre_b = nullptr;
ggml_tensor * mm_norm_mid_w = nullptr;
// qwen3a
ggml_tensor * conv2d_1_w = nullptr;
ggml_tensor * conv2d_1_b = nullptr;
ggml_tensor * conv2d_2_w = nullptr;
ggml_tensor * conv2d_2_b = nullptr;
ggml_tensor * conv2d_3_w = nullptr;
ggml_tensor * conv2d_3_b = nullptr;
// cogvlm
ggml_tensor * mm_post_fc_norm_w = nullptr;
ggml_tensor * mm_post_fc_norm_b = nullptr;