diff --git a/monai/networks/nets/regunet.py b/monai/networks/nets/regunet.py
index 4d6150ea1b..c8f9829bae 100644
--- a/monai/networks/nets/regunet.py
+++ b/monai/networks/nets/regunet.py
@@ -295,7 +295,7 @@ def affine_transform(self, theta: torch.Tensor):
 
     def forward(self, x: list[torch.Tensor], image_size: list[int]) -> torch.Tensor:
         f = x[0]
-        self.grid = self.grid.to(device=f.device)
+        self.grid = self.grid.to(device=f.device, dtype=f.dtype)
         theta = self.fc(f.reshape(f.shape[0], -1))
         if self.save_theta:
             self.theta = theta.detach()
diff --git a/tests/networks/nets/test_globalnet.py b/tests/networks/nets/test_globalnet.py
index ecb0243a1b..fcb0218aec 100644
--- a/tests/networks/nets/test_globalnet.py
+++ b/tests/networks/nets/test_globalnet.py
@@ -98,6 +98,20 @@ def test_script(self, input_param, input_shape, _):
         test_data = torch.randn(input_shape)
         test_script_save(net, test_data)
 
+    @parameterized.expand(TEST_CASES_GLOBAL_NET)
+    def test_half_precision_forward(self, input_param, input_shape, expected_shape):
+        # AffineHead.grid was a plain float32 attribute, moved by device only
+        # (`self.grid.to(device=f.device)`) in forward(). Casting the network to half
+        # precision left `self.grid` at float32 while theta became float16, and
+        # `affine_transform`'s einsum raised `RuntimeError: expected scalar type Half
+        # but found Float` on the very first half-precision forward call.
+        net = GlobalNet(**input_param).half()
+        with eval_mode(net):
+            img = torch.randn(input_shape, dtype=torch.float16)
+            result = net(img)
+            self.assertEqual(result.dtype, torch.float16)
+            self.assertEqual(result.shape, expected_shape)
+
 
 if __name__ == "__main__":
     unittest.main()