onnxruntime

4af62918 - Refine `op_types_to_quantize` argument handling in matmul_4bits_quantizer.py (#21815)

Refine `op_types_to_quantize` argument handling in matmul_4bits_quantizer.py (#21815) ### Description <!-- Describe your changes. --> Refine `op_types_to_quantize` argument handling in matmul_4bits_quantizer.py ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> The default `op_types_to_quantize "MatMul"` will cause `tuple(args.op_types_to_quantize)` to become `('M', 'a', 't', 'M', 'u', 'l')`, which is not expected.