Skip to content
Optimization

SmoothQuant

W8A8 quantization technique that migrates quantization difficulty from activations to weights via a mathematically equivalent per-channel scaling.

Definition

SmoothQuant (Xiao et al., 2022) addresses the challenge of quantizing activations, which contain large outliers that undermine per-tensor INT8 quantization. It applies a channel-wise scaling factor that reduces activation variance while inversely scaling the corresponding weight channels — a mathematically equivalent transformation — so that both activations and weights become quantization-friendly. The result is a W8A8 model with near-FP16 accuracy that enables hardware-efficient inference on GPUs with INT8 Tensor Core support.

More Optimization terms