fix sglang infer hang (#5108)

Author: Jintao-Huang

swift/llm/infer/infer_engine/infer_engine.py

@@ -72,7 +72,11 @@ async def _run_async_iter():
             else:
                 queue.put(None)
 
-        loop = asyncio.new_event_loop()
+        try:
+            loop = asyncio.get_event_loop()
+        except RuntimeError:
+            loop = asyncio.new_event_loop()
+            asyncio.set_event_loop(loop)
         thread = Thread(target=lambda: loop.run_until_complete(_run_async_iter()))
         thread.start()
         pre_output = None
@@ -81,7 +85,6 @@ async def _run_async_iter():
             if output is None or isinstance(output, Exception):
                 prog_bar.update()
                 self._update_metrics(pre_output, metrics)
-                loop.close()
                 return
             pre_output = output
             yield output

swift/llm/infer/infer_engine/sglang_engine.py

@@ -90,18 +90,15 @@ def _load_generation_config(self) -> None:
         generation_config_path = os.path.join(self.model_dir, 'generation_config.json')
         if os.path.isfile(generation_config_path):
             generation_config = GenerationConfig.from_pretrained(self.model_dir)
-            kwargs = generation_config.to_dict()
-            top_k = kwargs.get('top_k')
-            if top_k == 0:
-                kwargs['top_k'] = -1
-
-            parameters = inspect.signature(SamplingParams).parameters
-            for k, v in kwargs.copy().items():
-                if k not in parameters or v is None:
-                    kwargs.pop(k)
-            self.generation_config = kwargs
         else:
-            self.generation_config = {}
+            generation_config = GenerationConfig()
+        kwargs = generation_config.to_dict()
+        top_k = kwargs.get('top_k')
+        if top_k == 0:
+            kwargs['top_k'] = -1
+
+        parameters = inspect.signature(SamplingParams).parameters
+        self.generation_config = {k: v for k, v in kwargs.items() if k in parameters and v is not None}
 
     def _prepare_generation_config(self, request_config: RequestConfig) -> Dict[str, Any]:
         kwargs = {'max_new_tokens': request_config.max_tokens}