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 2, 01:00 UTC
[CI/Build] Fix LoRA testing (#44425)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Jee Jee Li committed
Jun 3, 2026 at 23:58 UTC
4d1fd13613ca056c5ffd46df9fab17012e93695c
1 file changed
+10
-4
vllm/entrypoints/openai/models/serving.py
+10
-4
@@ -194,10 +194,16 @@ class OpenAIServingModels:
194
lora_request.lora_name, lora_request.lora_path
195
)
196
) in str(e):
197
- raise LoRAAdapterNotFoundError(
198
- lora_request.lora_name, lora_request.lora_path
199
- ) from e
200
- raise
197
+ return create_error_response(
198
+ LoRAAdapterNotFoundError(
199
+ lora_request.lora_name, lora_request.lora_path
200
+ )
201
+ )
202
+ return create_error_response(
203
+ message=str(e),
204
+ err_type="InternalServerError",
205
+ status_code=HTTPStatus.INTERNAL_SERVER_ERROR,
206
+ )
207
208
self.lora_requests[lora_name] = lora_request
209
logger.info(