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 9, 05:00 UTC
support return prompt token ids in responses (#33378)
cmunley1 committed
Jan 31, 2026 at 06:04 UTC
6f5e7cda57e973ccb7fca22862e107119515b33a
1 file changed
+1
-2
vllm/entrypoints/openai/responses/protocol.py
+1
-2
@@ -222,8 +222,7 @@ class ResponsesRequest(OpenAIBaseModel):
222
default=False,
223
description=(
224
"Dictates whether or not to return messages as part of the "
225
- "response object. Currently only supported for"
226
- "non-background and gpt-oss only. "
225
+ "response object. Currently only supported for non-background."
226
),
227
)
228
# similar to input_messages / output_messages in ResponsesResponse