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
@@ -111,6 +111,15 @@ struct mtmd_audio_preprocessor_qwen3a : mtmd_audio_preprocessor {
    mtmd_audio_cache cache;
 };

+struct mtmd_audio_preprocessor_mimo_audio : mtmd_audio_preprocessor {
+    mtmd_audio_preprocessor_mimo_audio(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
+    void initialize() override;
+    bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
+
+  private:
+    mtmd_audio_cache cache;
+};
+
 //
 // streaming ISTFT - converts spectrogram frames back to audio one frame at a time
 //