From 8c8d9652ab85b84f8b1b00cbdc9a9569fdd0f86c Mon Sep 17 00:00:00 2001
From: Jorge Pineda <jorgep31415@meta.com>
Date: Fri, 31 May 2024 12:06:33 -0700
Subject: [PATCH] Enable operator<< for Half tensor (#3779)

Summary:
Pull Request resolved: https://github.com/pytorch/executorch/pull/3779

Useful for debugging `Half` i.e. `fp16` models, when we have `EValue`s that are `Half` dtype and we do the following:
```
std::cout << "===== INPUT =====" << std::endl;
for (EValue& v : inputs) {
  std::cout << v << std::endl;
}

std::cout << "===== OUTPUT =====" << std::endl;
for (EValue& v : outputs) {
  std::cout << v << std::endl;
}
```

## Before
```
===== INPUT =====
tensor(sizes=[1, 3, 96, 72], [<unhandled scalar type 5>])
===== OUTPUT =====
tensor(sizes=[1, 2, 96, 72], [<unhandled scalar type 5>])
```

## After
```
===== INPUT =====
tensor(sizes=[1, 3, 96, 72], [0.279785, 0.271484, 0.364746, ..., 0.150391, 0.836426, 0.019043])
===== OUTPUT =====
tensor(sizes=[1, 2, 96, 72], [18.2344, -10.0938, 1.35059, ..., -33.6875, 4.07422, -22.5312])
```
ghstack-source-id: 228461839

Reviewed By: copyrightly

Differential Revision: D57977366

fbshipit-source-id: a9ba1c11f75af85dcf7c91b9b06b4ec3333455bc
---
 extension/evalue_util/print_evalue.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/extension/evalue_util/print_evalue.cpp b/extension/evalue_util/print_evalue.cpp
index efef4c414f..21180cf5d2 100644
--- a/extension/evalue_util/print_evalue.cpp
+++ b/extension/evalue_util/print_evalue.cpp
@@ -158,7 +158,7 @@ void print_tensor(std::ostream& os, exec_aten::Tensor tensor) {
     break;
 
   switch (tensor.scalar_type()) {
-    ET_FORALL_REAL_TYPES_AND(Bool, PRINT_TENSOR_DATA)
+    ET_FORALL_REAL_TYPES_AND2(Bool, Half, PRINT_TENSOR_DATA)
     default:
       os << "[<unhandled scalar type " << (int)tensor.scalar_type() << ">]";
   }