Fixed params issue in Google Vertex ai

CHANGELOG.md

@@ -13,6 +13,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed an issue in `SmallWebRTCTransport` where an error was thrown if the 
   client did not create a video transceiver.
 
+- Fixed an issue where llm input parameters were not working and applied correctly in `GoogleVertexLLMService`, causing 
+  unexpected behavior during inference.
+
 ## [0.0.63] - 2025-04-11
 
 ### Added

src/pipecat/services/google/llm_vertex.py

@@ -65,7 +65,7 @@ class GoogleVertexLLMService(OpenAILLMService):
         base_url = self._get_base_url(params)
         self._api_key = self._get_api_token(credentials, credentials_path)
 
-        super().__init__(api_key=self._api_key, base_url=base_url, model=model, **kwargs)
+        super().__init__(api_key=self._api_key, base_url=base_url, model=model,params=params, **kwargs)
 
     @staticmethod
     def _get_base_url(params: InputParams) -> str: