diff --git a/guidance/llms/_llama_cpp.py b/guidance/llms/_llama_cpp.py
index dd0fa1813..c985af59e 100644
--- a/guidance/llms/_llama_cpp.py
+++ b/guidance/llms/_llama_cpp.py
@@ -283,7 +283,7 @@ async def __call__(self, prompt, stop=None, stop_regex=None, temperature=None, n
             token_healing = self.llm.token_healing
 
         # generate the cache key
-        key = self._cache_key(locals())
+        key = self._gen_key(locals())
 
         # set the stop patterns
         if stop is not None:
@@ -778,4 +778,4 @@ def __next__(self):
             if value is None:
                 raise StopIteration()
             else:
-                return value
\ No newline at end of file
+                return value