diff --git a/llama_stack/core/routers/inference.py b/llama_stack/core/routers/inference.py index 88099acd0..762d7073e 100644 --- a/llama_stack/core/routers/inference.py +++ b/llama_stack/core/routers/inference.py @@ -739,6 +739,7 @@ class InferenceRouter(Inference): id = None created = None choices_data: dict[int, dict[str, Any]] = {} + try: async for chunk in response: # Skip None chunks