Revert "Supress verbose logs from model_hosting_container_standards (… (#29335)

Signed-off-by: Shen Teng <sheteng@amazon.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

requirements/common.txt

@@ -49,4 +49,4 @@ cbor2 # Required for cross-language serialization of hashable objects
 setproctitle # Used to set process names for better debugging and monitoring
 openai-harmony >= 0.0.3  # Required for gpt-oss
 anthropic == 0.71.0
-model-hosting-container-standards < 1.0.0
+model-hosting-container-standards >= 0.1.9, < 1.0.0
\ No newline at end of file

vllm/entrypoints/openai/api_server.py

@@ -5,7 +5,6 @@ import hashlib
 import importlib
 import inspect
 import json
-import logging
 import multiprocessing
 import multiprocessing.forkserver as forkserver
 import os
@@ -2099,9 +2098,6 @@ async def run_server(args, **uvicorn_kwargs) -> None:
     # Add process-specific prefix to stdout and stderr.
     decorate_logs("APIServer")
 
-    # Suppress verbose logs from model_hosting_container_standards
-    logging.getLogger("model_hosting_container_standards").setLevel(logging.ERROR)
-
     listen_address, sock = setup_server(args)
     await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)