update arg_utils.py

vllm/engine/arg_utils.py

@@ -1594,6 +1594,9 @@ class EngineArgs:
         # For pooling tasks the default is False
         if model_config.runner_type != "pooling":
             self.enable_chunked_prefill = True
+            if model_config.enable_chunked_prefill is not None and \
+                model_config.enable_chunked_prefill is False:
+                self.enable_chunked_prefill = False
             if self.enable_prefix_caching is None:
                 self.enable_prefix_caching = True
         else: