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
[Frontend] Fix logging format when enable response logging (#28049)
Signed-off-by: esmeetu <jasonailu87@gmail.com>
Roy Wang committed
Nov 7, 2025 at 00:25 UTC
d1dd5f53e4bdb78d5e3b7b4dc1c03f6e2a991e1e
1 file changed
+1
-2
vllm/entrypoints/openai/api_server.py
+1
-2
@@ -1572,8 +1572,7 @@ def _log_streaming_response(response, response_body: list) -> None:
1572
full_content = full_content[:2048] + ""
1573
"...[truncated]"
1574
logger.info(
1575
- "response_body={streaming_complete: "
1576
- "content='%s', chunks=%d}",
1575
+ "response_body={streaming_complete: content=%r, chunks=%d}",
1576
full_content,
1577
chunk_count,
1578
)