SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Tests: upgrade test_eager_matches_sdpa_generate (#34386)

Browse Source
This commit is contained in:
Joao Gante
2024-10-25 11:55:07 +01:00
committed by GitHub
parent 8814043c8c
commit 186b8dc190
22 changed files with 85 additions and 946 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
tests/models/falcon/test_modeling_falcon.py
View File

@@ -14,7 +14,6 @@
# limitations under the License.
"""Testing suite for the PyTorch Falcon model."""
import tempfile
import unittest
from parameterized import parameterized
@@ -27,7 +26,6 @@ from transformers import (
set_seed,
)
from transformers.testing_utils import (
is_flaky,
require_bitsandbytes,
require_torch,
require_torch_sdpa,
@@ -520,78 +518,6 @@ class FalconModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMix
torch.testing.assert_close(ntk_sin_long, original_sin_long)
self.assertTrue((ntk_scaling_rope.inv_freq <= original_rope.inv_freq).all())
# TODO: @Fxmarty
@is_flaky(max_attempts=3, description="flaky on some models.")
@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")
# NOTE: This check is disabled for Falcon as the non-SDPA/SDPA implementation is in the same class (legacy reason).
# for name, submodule in model_eager.named_modules():
# if "SdpaAttention" in submodule.__class__.__name__:
# raise ValueError("The eager model should not have SDPA attention layers")
# has_sdpa = False
# for name, submodule in model_sdpa.named_modules():
# if "SdpaAttention" in submodule.__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 FalconLanguageGenerationTest(unittest.TestCase):