[OMNIML-2336] make w4a8_nvfp4_fp8's scale factor in range of 448/6#406

sychen52 merged 1 commit intoNVIDIA:mainNVIDIA/TensorRT-Model-Optimizer:mainfrom

sychen52:448/6sychen52/TensorRT-Model-Optimizer:448/6Copy head branch name to clipboard