[V1][Bugfix]: vllm v1 verison metric num_gpu_blocks is None (#15755)

Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>

vllm/v1/engine/async_llm.py

@@ -120,7 +120,8 @@ class AsyncLLM(EngineClient):
             executor_class=executor_class,
             log_stats=self.log_stats,
         )
-
+        for stat_logger in self.stat_loggers[0]:
+            stat_logger.log_engine_initialized()
         self.output_handler: Optional[asyncio.Task] = None
         try:
             # Start output handler eagerly if we are in the asyncio eventloop.