[BugFix] fix control signal release failed (#3374)

* [BugFix]

* [BugFix]

* [BugFix]

* [BugFix]

* fix

* fix

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

fastdeploy/entrypoints/openai/serving_completion.py

@@ -101,6 +101,13 @@ class OpenAIServingCompletion:
         api_server_logger.info(f"start inference for request {num_choices}")
         prompt_batched_token_ids = []
         text_after_process_list = []
+        try:
+            if self.max_waiting_time < 0:
+                await self.engine_client.semaphore.acquire()
+            else:
+                await asyncio.wait_for(self.engine_client.semaphore.acquire(), timeout=self.max_waiting_time)
+        except Exception:
+            return ErrorResponse(code=408, message=f"Request queued time exceed {self.max_waiting_time}")
         try:
             for idx, prompt in enumerate(request_prompts):
                 request_id_idx = f"{request_id}-{idx}"
@@ -117,14 +124,6 @@ class OpenAIServingCompletion:
 
                 del current_req_dict
 
-            try:
-                if self.max_waiting_time < 0:
-                    await self.engine_client.semaphore.acquire()
-                else:
-                    await asyncio.wait_for(self.engine_client.semaphore.acquire(), timeout=self.max_waiting_time)
-            except Exception:
-                return ErrorResponse(code=408, message=f"Request queued time exceed {self.max_waiting_time}")
-
             if request.stream:
                 return self.completion_stream_generator(
                     request=request,