[OMNIML-6284] Make awq_lite independent of how the calibration tokens are batched - #2996

[OMNIML-6284] Make awq_lite independent of how the calibration tokens are batched#2996

shengliangxu wants to merge 1 commit into

mainNVIDIA/Model-Optimizer:mainfrom

shengliangx/awq-lite-token-weightedNVIDIA/Model-Optimizer:shengliangx/awq-lite-token-weightedCopy head branch name to clipboard