Stefan S. Tomic

Bias-Aware FP8 Format for Efficient Weight Representation in Post-Training Quantization

Deep neural network (DNN) weights dominate memory consumption during inference, making their efficient numerical representation particularly important for resource-constrained Edge AI systems. Widely used 8-bit floating-point (FP8) formats, such as E5M2 and E4M3, provide representable ranges that are significantly wide...