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 16, 00:45 UTC
[Misc] fix typo: add missing space in lora adapter error message (#12564)
Signed-off-by: Beim <beim2015@outlook.com>
Beim committed
Jan 31, 2025 at 04:39 UTC
41bf5612f590dd13fa5e5dec083849ab6cde2f70
1 file changed
+1
-1
vllm/entrypoints/openai/serving_models.py
+1
-1
@@ -203,7 +203,7 @@ class OpenAIServingModels:
203
for lora_request in self.lora_requests):
204
return create_error_response(
205
message=
206
- f"The lora adapter '{request.lora_name}' has already been"
206
+ f"The lora adapter '{request.lora_name}' has already been "
207
"loaded.",
208
err_type="InvalidUserInput",
209
status_code=HTTPStatus.BAD_REQUEST)