A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 04:15 UTC
Removed Extraneous Print Message From OAI Server (#3440)
Robert Shaw committed
Mar 15, 2024 at 19:35 UTC
10585e035ec564cd376146c3fe5ffe427a43c92c
1 file changed
-3
vllm/entrypoints/openai/serving_completion.py
-3
@@ -309,10 +309,7 @@ class OpenAIServingCompletion(OpenAIServing):
309
except ValueError as e:
310
# TODO: Use a vllm-specific Validation Error
311
data = self.create_streaming_error_response(str(e))
312
- print("yield", f"data: {data}\n\n")
312
yield f"data: {data}\n\n"
314
-
315
- print("yield", "data: [DONE]\n\n")
313
yield "data: [DONE]\n\n"
314
315
def request_output_to_completion_response(