diff --git a/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py b/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py index 91819a2078c77..1d91141a117ad 100644 --- a/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py +++ b/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py @@ -280,7 +280,7 @@ def __init__( super().__init__( algorithm="nvidia_awq", - quant_format=quant_format, + quant_format=QuantFormat.QDQ, op_types_to_quantize=None, # Assuming op_types_to_quantize is handled elsewhere quant_axes=None, # Assuming quant_axes is handled elsewhere )