fix

Author: sayakpaul

tests/quantization/bnb/test_4bit.py

@@ -873,7 +873,7 @@ def test_fp4_double_safe(self):
 
 @require_torch_version_greater("2.7.1")
 @require_bitsandbytes_version_greater("0.45.5")
-class Bnb4BitCompileTests(QuantCompileTests):
+class Bnb4BitCompileTests(QuantCompileTests, unittest.TestCase):
     @property
     def quantization_config(self):
         return PipelineQuantizationConfig(

tests/quantization/bnb/test_mixed_int8.py

@@ -838,7 +838,7 @@ def test_serialization_sharded(self):
 
 @require_torch_version_greater_equal("2.6.0")
 @require_bitsandbytes_version_greater("0.45.5")
-class Bnb8BitCompileTests(QuantCompileTests):
+class Bnb8BitCompileTests(QuantCompileTests, unittest.TestCase):
     @property
     def quantization_config(self):
         return PipelineQuantizationConfig(

tests/quantization/gguf/test_gguf.py

@@ -654,7 +654,7 @@ def get_dummy_inputs(self):
 
 
 @require_torch_version_greater("2.7.1")
-class GGUFCompileTests(QuantCompileTests):
+class GGUFCompileTests(QuantCompileTests, unittest.TestCase):
     torch_dtype = torch.bfloat16
     gguf_ckpt = "https://huggingface.co/city96/FLUX.1-dev-gguf/blob/main/flux1-dev-Q2_K.gguf"
 

tests/quantization/test_torch_compile_utils.py

@@ -13,7 +13,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 import gc
-import unittest
 
 import torch
 
@@ -23,7 +22,7 @@
 
 @require_torch_gpu
 @slow
-class QuantCompileTests(unittest.TestCase):
+class QuantCompileTests:
     @property
     def quantization_config(self):
         raise NotImplementedError(

tests/quantization/torchao/test_torchao.py

@@ -630,7 +630,7 @@ def test_int_a16w8_cpu(self):
 
 
 @require_torchao_version_greater_or_equal("0.7.0")
-class TorchAoCompileTest(QuantCompileTests):
+class TorchAoCompileTest(QuantCompileTests, unittest.TestCase):
     @property
     def quantization_config(self):
         return PipelineQuantizationConfig(