Open access
2026
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...
A. Jovanovic, Stefan S. Tomic, Jelena R. Nikolić et al.
· IEEE Access · 0 citations