Public
  1. Public

onnxruntime

Public

Commits

Edward ChenGitHub
efdcefcf8ce
Edward Chen authored and GitHub committed 4190c29d226
Add MatMulNBits accuracy_level parameter to quantization utilities. (#19015)

Allow MatMulNBits `accuracy_level` attribute (added in #17669) to be set to a particular value when the model is quantized.