[OMNIML-6085] [2/3] Keep hf_ptq's previews in lockstep on a sharded model, and pin whole-model loads by plan - #3139

[OMNIML-6085] [2/3] Keep hf_ptq's previews in lockstep on a sharded model, and pin whole-model loads by plan#3139

shengliangxu wants to merge 6 commits into

shengliangx/hfep-base-14-hf-ptqNVIDIA/Model-Optimizer:shengliangx/hfep-base-14-hf-ptqfrom

shengliangx/hfep-14b-hf-ptq-previewsNVIDIA/Model-Optimizer:shengliangx/hfep-14b-hf-ptq-previewsCopy head branch name to clipboard