ci : adjust params for less runtime (#16167)

* ci : adjust params for less runtime

* ci : gate BF16 on some hardware

* ci : move extra tests to Arm runner

tools/main/main.cpp

@@ -178,7 +178,7 @@ int main(int argc, char ** argv) {
             return 1;
         }
 
-        // Start the non-batch threadpool in the paused state
+        // start the non-batch threadpool in the paused state
         tpp.paused = true;
     }