diff --git a/vllm/entrypoints/openai/api_server.py b/vllm/entrypoints/openai/api_server.py index 993a834e..9f29b4ac 100644 --- a/vllm/entrypoints/openai/api_server.py +++ b/vllm/entrypoints/openai/api_server.py @@ -160,6 +160,7 @@ async def validation_exception_handler(_, exc): @app.get("/health") async def health() -> Response: """Health check.""" + await openai_serving_chat.engine.check_health() return Response(status_code=200)