Make torch xla available on GPU (#29334)

* add USE_TORCH_XLA env

* rename torch_tpu to torch_xla

* better is_torch_xla_available; fix some fsdp and performance issues

* fix format

* fix bug when pjrt_device is cpu

* fix bug

* fix the deprecation handling

---------

Co-authored-by: anw90 <ang868@gmail.com>
Co-authored-by: wangang.wa <wangang.wa@alibaba-inc.com>

examples/pytorch/old_test_xla_examples.py

@@ -21,7 +21,7 @@ import sys
 from time import time
 from unittest.mock import patch
 
-from transformers.testing_utils import TestCasePlus, require_torch_tpu
+from transformers.testing_utils import TestCasePlus, require_torch_xla
 
 
 logging.basicConfig(level=logging.DEBUG)
@@ -44,7 +44,7 @@ stream_handler = logging.StreamHandler(sys.stdout)
 logger.addHandler(stream_handler)
 
 
-@require_torch_tpu
+@require_torch_xla
 class TorchXLAExamplesTests(TestCasePlus):
     def test_run_glue(self):
         import xla_spawn