Add MoE dispatch/combine fake quantization for vLLM's DeepGEMM Mega-MoE - #2767

Add MoE dispatch/combine fake quantization for vLLM's DeepGEMM Mega-MoE#2767

sychen52 merged 2 commits into

NVIDIA:mainNVIDIA/Model-Optimizer:mainfrom

sychen52:ep_comms_megamoesychen52/Model-Optimizer:ep_comms_megamoeCopy head branch name to clipboard