MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers
By Md. Mehrab Hossain Opi · Paper · cs.CV
Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices. However, existing PTQ methods typically employ uniform bit-widths across transformer components, overlooking their heterogeneous sensiti