[OMNIML-6073] [2/2] Calibrate fused experts on grouped_mm and torch_a2a instead of forcing eager - #3074

[OMNIML-6073] [2/2] Calibrate fused experts on grouped_mm and torch_a2a instead of forcing eager#3074

shengliangxu merged 42 commits into

mainNVIDIA/Model-Optimizer:mainfrom

shengliangx/hfep-8a-grouped-mm-calibrationNVIDIA/Model-Optimizer:shengliangx/hfep-8a-grouped-mm-calibrationCopy head branch name to clipboard