[SWDEV-539119] [rocm7.0_internal_testing] Add fast_tanh support (#2501)

Cherry picked from #2484

Author: jataylo

torch/_inductor/codegen/triton.py

@@ -1250,7 +1250,7 @@ def tan(x):
     @staticmethod
     @maybe_upcast_float32()
     def tanh(x):
-        return f"libdevice.tanh({x})"
+        return f"libdevice.fast_tanhf({x})"
 
     @staticmethod
     @maybe_upcast_float32()