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 11, 15:00 UTC
Make the `httpx` logger less annoying when Transformers v5 is installed (#30480)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Dec 11, 2025 at 15:44 UTC
97a042f3bca53417de6405a248e3d11fca568e2c
1 file changed
+5
vllm/logger.py
+5
@@ -229,6 +229,11 @@ def suppress_logging(level: int = logging.INFO) -> Generator[None, Any, None]:
229
# guaranteed by the Python GIL.
230
_configure_vllm_root_logger()
231
232
+# Transformers uses httpx to access the Hugging Face Hub. httpx is quite verbose,
233
+# so we set its logging level to WARNING when vLLM's logging level is INFO.
234
+if envs.VLLM_LOGGING_LEVEL == "INFO":
235
+ logging.getLogger("httpx").setLevel(logging.WARNING)
236
+
237
logger = init_logger(__name__)
238
239