fix: include user-defined LLM families in _resolve_architectures

The _resolve_architectures method only looked up architectures from
BUILTIN_LLM_FAMILIES, which caused custom-registered models with a
model_family pointing to a user-defined model to fail architecture
resolution. Now combines both builtin and user-defined families.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Author: yuj

xinference/model/llm/llm_family.py

@@ -168,9 +168,13 @@ def _resolve_architectures(self) -> Optional[List[str]]:
             return self.architectures
         if not self.model_family:
             return None
-        for family in BUILTIN_LLM_FAMILIES:
-            if family.model_name == self.model_family:
-                return family.architectures
+        from .custom import get_user_defined_llm_families
+
+        user_defined = {f.model_name: f for f in get_user_defined_llm_families()}
+        all_families = {f.model_name: f for f in BUILTIN_LLM_FAMILIES}
+        all_families.update(user_defined)
+        if self.model_family in all_families:
+            return all_families[self.model_family].architectures
         return None
 
     def has_architecture(self, *architectures: str) -> bool: