add tests

Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>

Author: kylesayrs

src/compressed_tensors/modeling/attention.py

@@ -99,9 +99,7 @@ def _ct_hooked_attention(module: Module, *args, **kwargs):
         return ALL_ATTENTION_FUNCTIONS[_original_impl](module, *args, **kwargs)
 
 
-def initialize_hooked_attention(
-    model: PreTrainedModel, module: Module, quantize: bool = True
-):
+def initialize_hooked_attention(model: PreTrainedModel, module: Module):
     """
     Initialize `QuantizedAttentionImpl` and `QuantizedKVCache` instances
     attached to attention

src/compressed_tensors/quantization/lifecycle/apply.py

@@ -29,7 +29,6 @@
     initialize_module_for_quantization,
     is_attention_module,
 )
-from compressed_tensors.quantization.quant_args import QuantizationArgs
 from compressed_tensors.quantization.quant_config import (
     QuantizationConfig,
     QuantizationStatus,