[core] add sleep and wake up endpoint and v1 support (#12987)

Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: cennn <2523403608@qq.com>
Co-authored-by: cennn <2523403608@qq.com>

vllm/engine/async_llm_engine.py

@@ -1187,6 +1187,12 @@ class AsyncLLMEngine(EngineClient):
     async def reset_prefix_cache(self) -> None:
         self.engine.reset_prefix_cache()
 
+    async def sleep(self, level: int = 1) -> None:
+        self.engine.sleep(level)
+
+    async def wake_up(self) -> None:
+        self.engine.wake_up()
+
     async def add_lora(self, lora_request: LoRARequest) -> None:
         self.engine.add_lora(lora_request)