using multi_gpu consistently (#8446)

* s|multiple_gpu|multi_gpu|g; s|multigpu|multi_gpu|g'

* doc

tests/test_modeling_common.py

@@ -23,7 +23,7 @@ from typing import List, Tuple
 
 from transformers import is_torch_available
 from transformers.file_utils import WEIGHTS_NAME
-from transformers.testing_utils import require_torch, require_torch_multigpu, slow, torch_device
+from transformers.testing_utils import require_torch, require_torch_multi_gpu, slow, torch_device
 
 
 if is_torch_available():
@@ -928,8 +928,8 @@ class ModelTesterMixin:
             with torch.no_grad():
                 model(**inputs)[0]
 
-    @require_torch_multigpu
-    def test_multigpu_data_parallel_forward(self):
+    @require_torch_multi_gpu
+    def test_multi_gpu_data_parallel_forward(self):
         config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
 
         # some params shouldn't be scattered by nn.DataParallel

tests/test_modeling_rag.py

@@ -29,7 +29,7 @@ from transformers.testing_utils import (
     require_sentencepiece,
     require_tokenizers,
     require_torch,
-    require_torch_non_multigpu,
+    require_torch_non_multi_gpu,
     slow,
     torch_device,
 )
@@ -581,7 +581,7 @@ class RagDPRT5Test(RagTestMixin, unittest.TestCase):
 @require_retrieval
 @require_sentencepiece
 @require_tokenizers
-@require_torch_non_multigpu
+@require_torch_non_multi_gpu
 class RagModelIntegrationTests(unittest.TestCase):
     @cached_property
     def sequence_model(self):

tests/test_modeling_reformer.py

@@ -20,7 +20,7 @@ from transformers.testing_utils import (
     require_sentencepiece,
     require_tokenizers,
     require_torch,
-    require_torch_multigpu,
+    require_torch_multi_gpu,
     slow,
     torch_device,
 )
@@ -562,8 +562,8 @@ class ReformerTesterMixin:
         config_and_inputs = self.model_tester.prepare_config_and_inputs()
         self.model_tester.create_and_check_reformer_model_fp16_generate(*config_and_inputs)
 
-    @require_torch_multigpu
-    def test_multigpu_data_parallel_forward(self):
+    @require_torch_multi_gpu
+    def test_multi_gpu_data_parallel_forward(self):
         # Opt-out of this test.
         pass
 

tests/test_modeling_transfo_xl.py

@@ -17,7 +17,7 @@ import random
 import unittest
 
 from transformers import is_torch_available
-from transformers.testing_utils import require_torch, require_torch_multigpu, slow, torch_device
+from transformers.testing_utils import require_torch, require_torch_multi_gpu, slow, torch_device
 
 from .test_configuration_common import ConfigTester
 from .test_generation_utils import GenerationTesterMixin
@@ -205,8 +205,8 @@ class TransfoXLModelTest(ModelTesterMixin, GenerationTesterMixin, unittest.TestC
         output_result = self.model_tester.create_transfo_xl_lm_head(*config_and_inputs)
         self.model_tester.check_transfo_xl_lm_head_output(output_result)
 
-    @require_torch_multigpu
-    def test_multigpu_data_parallel_forward(self):
+    @require_torch_multi_gpu
+    def test_multi_gpu_data_parallel_forward(self):
         # Opt-out of this test.
         pass
 

tests/test_trainer_distributed.py

@@ -2,7 +2,7 @@ import sys
 from typing import Dict
 
 from transformers import EvalPrediction, HfArgumentParser, TrainingArguments, is_torch_available
-from transformers.testing_utils import TestCasePlus, execute_subprocess_async, require_torch_multigpu
+from transformers.testing_utils import TestCasePlus, execute_subprocess_async, require_torch_multi_gpu
 from transformers.utils import logging
 
 
@@ -44,7 +44,7 @@ if is_torch_available():
 
 
 class TestTrainerDistributed(TestCasePlus):
-    @require_torch_multigpu
+    @require_torch_multi_gpu
     def test_trainer(self):
 
         distributed_args = f"""