Time to Say Goodbye, torch 1.7 and 1.8 (#22291)

* time to say goodbye, torch 1.7 and 1.8

* clean up torch_int_div

* clean up is_torch_less_than_1_8-9

* update

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

tests/models/bloom/test_modeling_bloom.py

@@ -38,10 +38,9 @@ if is_torch_available():
         BloomModel,
         BloomTokenizerFast,
     )
-    from transformers.pytorch_utils import is_torch_greater_or_equal_than_1_10, is_torch_less_than_1_9
+    from transformers.pytorch_utils import is_torch_greater_or_equal_than_1_10
 else:
     is_torch_greater_or_equal_than_1_10 = False
-    is_torch_less_than_1_9 = True
 
 
 @require_torch
@@ -751,9 +750,6 @@ class BloomEmbeddingTest(unittest.TestCase):
                 self.assertAlmostEqual(EMBEDDINGS_DS_AFTER_LN[key][idx], output_dict_norm[key][idx], places=1)
 
     @require_torch
-    @unittest.skipIf(
-        is_torch_less_than_1_9, reason="Test failed with torch < 1.9 (`min_cuda` not implemented for `BFloat16`)"
-    )
     def test_hidden_states_transformers(self):
         cuda_available = torch.cuda.is_available()
         model = BloomModel.from_pretrained(self.path_bigscience_model, use_cache=False, torch_dtype="auto").to(

tests/models/mctct/test_modeling_mctct.py

@@ -32,9 +32,6 @@ if is_torch_available():
     import torch
 
     from transformers import MCTCTForCTC, MCTCTModel, MCTCTProcessor
-    from transformers.pytorch_utils import is_torch_less_than_1_9
-else:
-    is_torch_less_than_1_9 = True
 
 
 class MCTCTModelTester:
@@ -265,7 +262,6 @@ class MCTCTModelTester:
 
 
 @require_torch
-@unittest.skipIf(is_torch_less_than_1_9, "MCTCT is only available in torch v1.9+")
 class MCTCTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase):
     all_model_classes = (MCTCTForCTC, MCTCTModel) if is_torch_available() else ()
     pipeline_model_mapping = (

tests/models/swin/test_modeling_swin.py

@@ -33,9 +33,7 @@ if is_torch_available():
 
     from transformers import SwinBackbone, SwinForImageClassification, SwinForMaskedImageModeling, SwinModel
     from transformers.models.swin.modeling_swin import SWIN_PRETRAINED_MODEL_ARCHIVE_LIST
-    from transformers.pytorch_utils import is_torch_less_than_1_9
-else:
-    is_torch_less_than_1_9 = True
+
 
 if is_vision_available():
     from PIL import Image
@@ -266,7 +264,6 @@ class SwinModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase):
     def test_multi_gpu_data_parallel_forward(self):
         pass
 
-    @unittest.skipIf(is_torch_less_than_1_9, reason="This test fails for SwinModel when torch < 1.9")
     def test_training_gradient_checkpointing(self):
         super().test_training_gradient_checkpointing()
 

tests/models/trajectory_transformer/test_modeling_trajectory_transformer.py

@@ -36,9 +36,6 @@ if is_torch_available():
     from transformers.models.trajectory_transformer.modeling_trajectory_transformer import (
         TRAJECTORY_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST,
     )
-    from transformers.pytorch_utils import is_torch_less_than_1_9
-else:
-    is_torch_less_than_1_9 = True
 
 
 class TrajectoryTransformerModelTester:
@@ -199,7 +196,6 @@ class TrajectoryTransformerModelTest(ModelTesterMixin, GenerationTesterMixin, Pi
         ).loss
         loss.backward()
 
-    @unittest.skipIf(is_torch_less_than_1_9, reason="This test fails for TrajectoryTransformerModel when torch < 1.9")
     def test_training_gradient_checkpointing(self):
         if not self.model_tester.is_training:
             return

tests/models/wav2vec2/test_modeling_wav2vec2.py

@@ -71,9 +71,6 @@ if is_torch_available():
         _compute_mask_indices,
         _sample_negative_indices,
     )
-    from transformers.pytorch_utils import is_torch_less_than_1_9, torch_int_div
-else:
-    is_torch_less_than_1_9 = True
 
 
 if is_torchaudio_available():
@@ -1217,7 +1214,9 @@ class Wav2Vec2UtilsTest(unittest.TestCase):
         sequence_length = 10
         hidden_size = 4
         num_negatives = 3
-        sequence = torch_int_div(torch.arange(sequence_length * hidden_size, device=torch_device), hidden_size)
+        sequence = torch.div(
+            torch.arange(sequence_length * hidden_size, device=torch_device), hidden_size, rounding_mode="floor"
+        )
         features = sequence.view(sequence_length, hidden_size)  # each value in vector consits of same value
         features = features[None, :].expand(batch_size, sequence_length, hidden_size).contiguous()
 
@@ -1245,7 +1244,9 @@ class Wav2Vec2UtilsTest(unittest.TestCase):
         mask = torch.ones((batch_size, sequence_length), dtype=torch.long, device=torch_device)
         mask[-1, sequence_length // 2 :] = 0
 
-        sequence = torch_int_div(torch.arange(sequence_length * hidden_size, device=torch_device), hidden_size)
+        sequence = torch.div(
+            torch.arange(sequence_length * hidden_size, device=torch_device), hidden_size, rounding_mode="floor"
+        )
         features = sequence.view(sequence_length, hidden_size)  # each value in vector consits of same value
         features = features[None, :].expand(batch_size, sequence_length, hidden_size).contiguous()
 
@@ -1651,10 +1652,6 @@ class Wav2Vec2ModelIntegrationTest(unittest.TestCase):
 
     @require_pyctcdecode
     @require_torchaudio
-    @unittest.skipIf(
-        is_torch_less_than_1_9,
-        reason="`torchaudio.functional.resample` needs torchaudio >= 0.9 which requires torch >= 0.9",
-    )
     def test_wav2vec2_with_lm(self):
         ds = load_dataset("common_voice", "es", split="test", streaming=True)
         sample = next(iter(ds))
@@ -1679,10 +1676,6 @@ class Wav2Vec2ModelIntegrationTest(unittest.TestCase):
 
     @require_pyctcdecode
     @require_torchaudio
-    @unittest.skipIf(
-        is_torch_less_than_1_9,
-        reason="`torchaudio.functional.resample` needs torchaudio >= 0.9 which requires torch >= 0.9",
-    )
     def test_wav2vec2_with_lm_pool(self):
         ds = load_dataset("common_voice", "es", split="test", streaming=True)
         sample = next(iter(ds))