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 14, 05:30 UTC
Fix pre-commit error in main (#22462)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Woosuk Kwon committed
Aug 7, 2025 at 08:54 UTC
399d2a10e23fcf37cc7a703d7de50ffecc7e0c6f
1 file changed
+18
-18
vllm/entrypoints/openai/serving_responses.py
+18
-18
@@ -422,24 +422,6 @@ class OpenAIServingResponses(OpenAIServing):
422
usage=usage,
423
)
424
425
- # Log complete response if output logging is enabled
426
- if self.enable_log_outputs and self.request_logger:
427
- output_text = ""
428
- if content:
429
- output_text = content
430
- elif reasoning_content:
431
- output_text = f"[reasoning: {reasoning_content}]"
432
-
433
- if output_text:
434
- self.request_logger.log_outputs(
435
- request_id=request.request_id,
436
- outputs=output_text,
437
- output_token_ids=final_output.token_ids,
438
- finish_reason=final_output.finish_reason,
439
- is_streaming=False,
440
- delta=False,
441
- )
442
-
425
if request.store:
426
async with self.response_store_lock:
427
stored_response = self.response_store.get(response.id)
@@ -469,6 +451,24 @@ class OpenAIServingResponses(OpenAIServing):
451
reasoning_content = None
452
content = final_output.text
453
454
+ # Log complete response if output logging is enabled
455
+ if self.enable_log_outputs and self.request_logger:
456
+ output_text = ""
457
+ if content:
458
+ output_text = content
459
+ elif reasoning_content:
460
+ output_text = f"[reasoning: {reasoning_content}]"
461
+
462
+ if output_text:
463
+ self.request_logger.log_outputs(
464
+ request_id=request.request_id,
465
+ outputs=output_text,
466
+ output_token_ids=final_output.token_ids,
467
+ finish_reason=final_output.finish_reason,
468
+ is_streaming=False,
469
+ delta=False,
470
+ )
471
+
472
output = []
473
if reasoning_content:
474
reasoning_item = ResponseReasoningItem(