[BERT] Add support for sdpa (#28802)

* Adding SDPA support for BERT

* Using the proper input name for testing model input in inference()

* Adding documentation for SDPA in BERT model page

* Use the stable link for the documentation

* Adding a gate to only call .contiguous() for torch < 2.2.0

* Additions and fixes to the documentation

* Minor updates to documentation

* Adding extra requirements needed for the contiguous() bug

* Adding "Adapted from" in plcae of the "Copied from"

* Add benchmark speedup tables to the documentation

* Minor fixes to the documentation

* Use ClapText as a replacemenet for Bert in the Copied-From

* Some more fixes for the fix-copies references

* Overriding the test_eager_matches_sdpa_generate in bert tests to not load with low_cpu_mem_usage

[test all]

* Undo changes to separate test

* Refactored SDPA self attention code for KV projections

* Change use_sdpa to attn_implementation

* Fix test_sdpa_can_dispatch_on_flash by preparing input (required for MultipleChoice models)

tests/models/bert/test_modeling_bert.py

@@ -18,7 +18,14 @@ import unittest
 
 from transformers import BertConfig, is_torch_available
 from transformers.models.auto import get_values
-from transformers.testing_utils import CaptureLogger, require_torch, require_torch_accelerator, slow, torch_device
+from transformers.testing_utils import (
+    CaptureLogger,
+    require_torch,
+    require_torch_accelerator,
+    require_torch_sdpa,
+    slow,
+    torch_device,
+)
 
 from ...generation.test_utils import GenerationTesterMixin
 from ...test_configuration_common import ConfigTester
@@ -621,6 +628,79 @@ class BertModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin
                 loaded = torch.jit.load(os.path.join(tmp, "bert.pt"), map_location=torch_device)
                 loaded(inputs_dict["input_ids"].to(torch_device), inputs_dict["attention_mask"].to(torch_device))
 
+    # This test was copied from the common test_eager_matches_sdpa_generate(), but without low_cpu_mem_usage=True.
+    # TODO: Remove this and use the parent method (in common tests) once BERT supports low_cpu_mem_usage=True.
+    @require_torch_sdpa
+    @slow
+    def test_eager_matches_sdpa_generate(self):
+        max_new_tokens = 30
+
+        if len(self.all_generative_model_classes) == 0:
+            self.skipTest(f"{self.__class__.__name__} tests a model that does support generate: skipping this test")
+
+        for model_class in self.all_generative_model_classes:
+            if not model_class._supports_sdpa:
+                self.skipTest(f"{model_class.__name__} does not support SDPA")
+
+            config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
+
+            dummy_input = inputs_dict[model_class.main_input_name]
+            if dummy_input.dtype in [torch.float32, torch.bfloat16]:
+                dummy_input = dummy_input.to(torch.float16)
+
+            # make sure that all models have enough positions for generation
+            if hasattr(config, "max_position_embeddings"):
+                config.max_position_embeddings = max_new_tokens + dummy_input.shape[1] + 1
+
+            model = model_class(config)
+
+            with tempfile.TemporaryDirectory() as tmpdirname:
+                model.save_pretrained(tmpdirname)
+
+                dummy_attention_mask = inputs_dict.get("attention_mask", torch.ones_like(dummy_input))
+
+                model_sdpa = model_class.from_pretrained(
+                    tmpdirname,
+                    torch_dtype=torch.float16,
+                    # low_cpu_mem_usage=True,
+                ).to(torch_device)
+
+                self.assertTrue(model_sdpa.config._attn_implementation == "sdpa")
+
+                model_eager = model_class.from_pretrained(
+                    tmpdirname,
+                    torch_dtype=torch.float16,
+                    # low_cpu_mem_usage=True,
+                    attn_implementation="eager",
+                ).to(torch_device)
+
+                self.assertTrue(model_eager.config._attn_implementation == "eager")
+
+                for name, submodule in model_eager.named_modules():
+                    class_name = submodule.__class__.__name__
+                    if "SdpaAttention" in class_name or "SdpaSelfAttention" in class_name:
+                        raise ValueError("The eager model should not have SDPA attention layers")
+
+                has_sdpa = False
+                for name, submodule in model_sdpa.named_modules():
+                    class_name = submodule.__class__.__name__
+                    if "SdpaAttention" in class_name or "SdpaSelfAttention" in class_name:
+                        has_sdpa = True
+                        break
+                if not has_sdpa:
+                    raise ValueError("The SDPA model should have SDPA attention layers")
+
+                # Just test that a large cache works as expected
+                res_eager = model_eager.generate(
+                    dummy_input, attention_mask=dummy_attention_mask, max_new_tokens=max_new_tokens, do_sample=False
+                )
+
+                res_sdpa = model_sdpa.generate(
+                    dummy_input, attention_mask=dummy_attention_mask, max_new_tokens=max_new_tokens, do_sample=False
+                )
+
+                self.assertTrue(torch.allclose(res_eager, res_sdpa))
+
 
 @require_torch
 class BertModelIntegrationTest(unittest.TestCase):