[PT FE] Support aten::pow_ (#21630)

* [PT FE] Support aten::pow_

* Fix tests

src/frontends/pytorch/src/op/pow.cpp

@@ -15,8 +15,17 @@ OutputVector translate_pow(const NodeContext& context) {
     num_inputs_check(context, 2, 2);
     auto lhs = context.get_input(0);
     auto rhs = context.get_input(1);
-    align_eltwise_input_types(context, lhs, rhs, true);
-    return {context.mark_node(std::make_shared<ov::op::v1::Power>(lhs, rhs))};
+    auto inplace = context.get_op_type() == "aten::pow_";
+    if (inplace) {
+        rhs = std::make_shared<ov::op::v1::ConvertLike>(rhs, lhs);
+    } else {
+        align_eltwise_input_types(context, lhs, rhs, true);
+    }
+    auto res = context.mark_node(std::make_shared<ov::op::v1::Power>(lhs, rhs));
+    if (inplace) {
+        context.mutate_input(0, res);
+    }
+    return {res};
 }
 
 }  // namespace op

src/frontends/pytorch/src/op_table.cpp

@@ -471,6 +471,7 @@ const std::map<std::string, CreatorFunction> get_supported_ops_ts() {
         {"aten::pixel_unshuffle", op::translate_pixel_unshuffle},
         {"aten::prelu", op::translate_1to1_match_2_inputs<opset10::PRelu>},
         {"aten::pow", op::translate_pow},
+        {"aten::pow_", op::translate_pow},
         {"aten::prod", op::translate_prod},
         {"aten::quantize_per_channel", op::translate_quantize_per_channel},
         {"aten::quantize_per_tensor", op::translate_quantize_per_tensor},