TR-PTQ: High-Accuracy Integer-Only Transformer Post Training Quantization via Taylor Region Reformulation
Post-training quantization (PTQ) enables efficient deployment, yet transformer architectures remain challenging to quantize due to nonlinear layers. While existing methods attribute accuracy loss to insufficient numerical precision, often necessitating floating-point fallbacks, we demonstrate that degradation is actual...
Eli S. Levy, Adam Teman, Yoni Pugachov
· 0 citations