diff --git a/vllm/entrypoints/api_server.py b/vllm/entrypoints/api_server.py index f3e80cab..ea3c93f7 100644 --- a/vllm/entrypoints/api_server.py +++ b/vllm/entrypoints/api_server.py @@ -66,7 +66,7 @@ async def generate(request: Request) -> Response: prompt + output.text for output in request_output.outputs ] ret = {"text": text_outputs} - yield (json.dumps(ret) + "\0").encode("utf-8") + yield (json.dumps(ret) + "\n").encode("utf-8") if stream: return StreamingResponse(stream_results())