update

Author: richardhuo-nv

src/triton_cli/templates/llmapi/1/model.py

@@ -142,6 +142,9 @@ def _get_sampling_config_from_request(self, request):
             None if kwargs["top_p"] is None or kwargs["top_p"] <= 0 else kwargs["top_p"]
         )
 
+        # Remove None values
+        kwargs = {k: v for k, v in kwargs.items() if v is not None}
+
         return kwargs
 
     @classmethod
@@ -244,6 +247,7 @@ def _auto_complete_inputs_and_outputs(auto_complete_model_config):
                 "name": "max_tokens",
                 "data_type": "TYPE_INT32",
                 "dims": [1],
+                "optional": True,
             },
             {
                 "name": "stop",