onnxruntime

0d26928b - Rename matmul_4bits_quantizer.py to matmul_nbits_quantizer.py (#24472)

Rename matmul_4bits_quantizer.py to matmul_nbits_quantizer.py (#24472) ### Description * Rename filename and class name since it supports 4 and 8 bits. * Update HQQWeightOnlyQuantizer to support 8 bits. * Update some comments. ### Motivation and Context https://github.com/microsoft/onnxruntime/pull/24384 added 8 bits support for the default weight only quantizer.