Update protobuf/model_config.proto

Co-authored-by: Yingge He <[email protected]>

Author: pskiran1

protobuf/model_config.proto

@@ -1662,8 +1662,8 @@ message ModelEnsembling
 
   //@@  .. cpp:var:: uint32 max_inflight_requests
   //@@
-  //@@     The maximum number of concurrent inflight requests at each ensemble
-  //@@     step.
+  //@@     The maximum number of concurrent inflight requests allowed at each ensemble
+  //@@     step per inference request.
   //@@     This limit prevents unbounded memory growth when decoupled models
   //@@     produce responses faster than downstream models can consume them.
   //@@     Default value is 0, which indicates that no limit is enforced.