diff --git a/src/llama_stack/providers/utils/inference/inference_store.py b/src/llama_stack/providers/utils/inference/inference_store.py index 45d411f51..003adfddb 100644 --- a/src/llama_stack/providers/utils/inference/inference_store.py +++ b/src/llama_stack/providers/utils/inference/inference_store.py @@ -35,6 +35,7 @@ class InferenceStore: self.reference = reference self.sql_store = None self.policy = policy + self.enable_write_queue = True # Async write queue and worker control self._queue: asyncio.Queue[tuple[OpenAIChatCompletion, list[OpenAIMessageParam]]] | None = None