update

tests/quantization/bnb/test_4bit.py

@@ -32,7 +32,8 @@ from diffusers import (
 )
 from diffusers.quantizers import PipelineQuantizationConfig
 from diffusers.utils import is_accelerate_version, logging
-from diffusers.utils.testing_utils import (
+
+from ...testing_utils import (
     CaptureLogger,
     backend_empty_cache,
     is_bitsandbytes_available,
@@ -50,7 +51,6 @@ from diffusers.utils.testing_utils import (
     slow,
     torch_device,
 )
-
 from ..test_torch_compile_utils import QuantCompileTests
 
 

tests/quantization/bnb/test_mixed_int8.py

@@ -32,7 +32,8 @@ from diffusers import (
 )
 from diffusers.quantizers import PipelineQuantizationConfig
 from diffusers.utils import is_accelerate_version
-from diffusers.utils.testing_utils import (
+
+from ...testing_utils import (
     CaptureLogger,
     backend_empty_cache,
     is_bitsandbytes_available,
@@ -51,7 +52,6 @@ from diffusers.utils.testing_utils import (
     slow,
     torch_device,
 )
-
 from ..test_torch_compile_utils import QuantCompileTests
 
 

tests/quantization/gguf/test_gguf.py

@@ -20,7 +20,8 @@ from diffusers import (
     WanVACETransformer3DModel,
 )
 from diffusers.utils import load_image
-from diffusers.utils.testing_utils import (
+
+from ...testing_utils import (
     Expectations,
     backend_empty_cache,
     backend_max_memory_allocated,
@@ -38,7 +39,6 @@ from diffusers.utils.testing_utils import (
     require_torch_version_greater,
     torch_device,
 )
-
 from ..test_torch_compile_utils import QuantCompileTests
 
 

tests/quantization/quanto/test_quanto.py

@@ -5,7 +5,8 @@ import unittest
 from diffusers import FluxPipeline, FluxTransformer2DModel, QuantoConfig
 from diffusers.models.attention_processor import Attention
 from diffusers.utils import is_optimum_quanto_available, is_torch_available
-from diffusers.utils.testing_utils import (
+
+from ...testing_utils import (
     backend_empty_cache,
     backend_reset_peak_memory_stats,
     enable_full_determinism,

tests/quantization/test_pipeline_level_quantization.py

@@ -22,7 +22,8 @@ from parameterized import parameterized
 from diffusers import BitsAndBytesConfig, DiffusionPipeline, QuantoConfig
 from diffusers.quantizers import PipelineQuantizationConfig
 from diffusers.utils import logging
-from diffusers.utils.testing_utils import (
+
+from ..testing_utils import (
     CaptureLogger,
     is_transformers_available,
     require_accelerate,

tests/quantization/test_torch_compile_utils.py

@@ -18,7 +18,8 @@ import inspect
 import torch
 
 from diffusers import DiffusionPipeline
-from diffusers.utils.testing_utils import backend_empty_cache, require_torch_accelerator, slow, torch_device
+
+from ..testing_utils import backend_empty_cache, require_torch_accelerator, slow, torch_device
 
 
 @require_torch_accelerator

tests/quantization/torchao/test_torchao.py

@@ -31,7 +31,8 @@ from diffusers import (
 )
 from diffusers.models.attention_processor import Attention
 from diffusers.quantizers import PipelineQuantizationConfig
-from diffusers.utils.testing_utils import (
+
+from ...testing_utils import (
     backend_empty_cache,
     backend_synchronize,
     enable_full_determinism,
@@ -45,7 +46,6 @@ from diffusers.utils.testing_utils import (
     slow,
     torch_device,
 )
-
 from ..test_torch_compile_utils import QuantCompileTests
 
 

tests/quantization/utils.py

@@ -1,5 +1,6 @@
 from diffusers.utils import is_torch_available
-from diffusers.utils.testing_utils import (
+
+from ..testing_utils import (
     backend_empty_cache,
     backend_max_memory_allocated,
     backend_reset_peak_memory_stats,