fix internal index.Tensor test on wrong device

Summary: After landing https://github.com/pytorch/pytorch/pull/69607, that made it an error to use indexing with `cpu_tensor[cuda_indices]`. There was one outstanding test in fbcode that incorrectly used indexing in that way, which is fixed here

Reviewed By: bottler, osalpekar

Differential Revision: D37128838

fbshipit-source-id: 611b6f717b5b5d89fa61fd9ebeb513ad7e65a656

tests/test_texturing.py

@@ -131,7 +131,7 @@ class TestTexturesVertex(TestCaseMixin, unittest.TestCase):
         )
 
         # define TexturesVertex
-        verts_texture = torch.rand(verts.shape)
+        verts_texture = torch.rand(verts.shape, device=device)
         textures = TexturesVertex(verts_features=verts_texture)
 
         # compute packed faces