[Frontend] Improve StreamingResponse Exception Handling (#11752)

2025-01-05 16:35:01 -05:00
parent eba17173d3
commit 33fc1e2e86
2 changed files with 3 additions and 3 deletions
--- a/vllm/entrypoints/openai/serving_completion.py
+++ b/vllm/entrypoints/openai/serving_completion.py
@@ -371,7 +371,7 @@ class OpenAIServingCompletion(OpenAIServing):
            # report to FastAPI middleware aggregate usage across all choices
            request_metadata.final_usage_info = final_usage_info

-        except ValueError as e:
+        except Exception as e:
            # TODO: Use a vllm-specific Validation Error
            data = self.create_streaming_error_response(str(e))
            yield f"data: {data}\n\n"