final fixes

Summary:

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:

Author: HDCharles

torchao/quantization/quant_api.py

@@ -454,7 +454,7 @@ def apply_int4_weight_only_quant(weight):
         preserve_zero = False
         zero_point_dtype = torch.bfloat16
         zero_point_domain = ZeroPointDomain.FLOAT
-        return to_affine_quantized_intx(weight, mapping_type, block_size, target_dtype, quant_min, quant_max, eps, zero_point_dtype=zero_point_dtype, preserve_zero=preserve_zero, zero_point_domain=zero_point_domain, layout_type=layout_type, use_hqq=use_hq)
+        return to_affine_quantized_intx(weight, mapping_type, block_size, target_dtype, quant_min, quant_max, eps, zero_point_dtype=zero_point_dtype, preserve_zero=preserve_zero, zero_point_domain=zero_point_domain, layout_type=layout_type, use_hqq=use_hqq)
 
     return _get_linear_subclass_inserter(apply_int4_weight_only_quant)