mtmd: support MiMo-V2.5 audio input (RVQ-based model) (#26190)

* gguf converter for mimo audio * fix conv * cpp impl * nits * nits 2
2026-07-27 23:17:09 +02:00
parent 0e4a036223
commit 1cbfd19883
15 changed files with 770 additions and 11 deletions
@@ -210,6 +210,11 @@ struct clip_graph_qwen3a : clip_graph {
    ggml_cgraph * build() override;
 };

+struct clip_graph_mimo_audio : clip_graph {
+    clip_graph_mimo_audio(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;