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 13, 17:00 UTC
[Misc] Remove the duplicate code (#28111)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Nov 6, 2025 at 10:07 UTC
07d614511f8b233650596a86b701faf0ad3a41a1
1 file changed
-5
vllm/entrypoints/openai/serving_responses.py
-5
@@ -1000,11 +1000,6 @@ class OpenAIServingResponses(OpenAIServing):
1000
# to add the tool call request to prev_outputs so that the
1001
# parse_response_input can find the tool call request when
1002
# parsing the tool call output.
1003
- if (
1004
- isinstance(response_msg, dict)
1005
- and response_msg.get("type") == "function_call"
1006
- ):
1007
- response_msg = ResponseFunctionToolCall.model_validate(response_msg)
1003
if isinstance(response_msg, ResponseFunctionToolCall):
1004
prev_outputs.append(response_msg)
1005
return messages