convert_hf_to_gguf: support split MTP export for HY V3 (#25641)

- Add a supports_mtp_export capability to ModelBase so architectures can opt
  into --mtp and --no-mtp without extending a central class allowlist.
- Enable the capability for the existing Qwen3.5/3.6 and Step3.5/3.7
  implementations, and for HY V3, whose converter already supports
  filtering the appended MTP layers.

conversion/hunyuan.py

@@ -361,6 +361,7 @@ class HunyuanVLTextModel(HunYuanModel):
 @ModelBase.register("HYV3ForCausalLM")
 class HYV3Model(TextModel):
     model_arch = gguf.MODEL_ARCH.HY_V3
+    supports_mtp_export = True
 
     # Trunk layer count, stashed before indexing so the classmethod
     # filter_tensors can identify the appended MTP block(s) (mirrors