Add int16 support to aten_bridge (#3069)

Summary:
Pull Request resolved: #3069

Running an executorch program via pybindings requires the aten_bridge. This currently fails if the model uses the `int16` dtype. This diff adds support for the type by adding it to the conversion switch statements.

Reviewed By: tarun292

Differential Revision: D56199304

fbshipit-source-id: 19a6815cf2885dda72febf247c3ca3bde91193a8

extension/aten_util/aten_bridge.cpp

@@ -68,6 +68,8 @@ torch::executor::ScalarType torchToExecuTorchScalarType(caffe2::TypeMeta type) {
       return torch::executor::ScalarType::Byte;
     case c10::ScalarType::Char:
       return torch::executor::ScalarType::Char;
+    case c10::ScalarType::Short:
+      return torch::executor::ScalarType::Short;
     case c10::ScalarType::Half:
       return torch::executor::ScalarType::Half;
     case c10::ScalarType::Int:
@@ -95,6 +97,8 @@ c10::ScalarType execuTorchtoTorchScalarType(torch::executor::ScalarType type) {
       return c10::ScalarType::Byte;
     case torch::executor::ScalarType::Char:
       return c10::ScalarType::Char;
+    case torch::executor::ScalarType::Short:
+      return c10::ScalarType::Short;
     case torch::executor::ScalarType::Half:
       return c10::ScalarType::Half;
     case torch::executor::ScalarType::Int: