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 15, 03:30 UTC
[Misc] Add security warning for development mode endpoints (#20508)
Signed-off-by: reidliu41 <reid201711@gmail.com>
Reid committed
Jul 5, 2025 at 11:52 UTC
7e908704919376cea9ff0f361596c1a0b14db1a3
1 file changed
+2
vllm/entrypoints/openai/api_server.py
+2
@@ -910,6 +910,8 @@ TASK_HANDLERS: dict[str, dict[str, tuple]] = {
910
}
911
912
if envs.VLLM_SERVER_DEV_MODE:
913
+ logger.warning("SECURITY WARNING: Development endpoints are enabled! "
914
+ "This should NOT be used in production!")
915
916
@router.get("/server_info")
917
async def show_server_info(raw_request: Request):