Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V

ArXi:2605.27003v1 Announce Type: cross W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitude activation outliers, and strongly timestep-dependent activation distributions across the multi-step denoising trajectory. These difficulties are compounded by Wan2.2-I2V's two-expert Mixture-of-Experts DiT design, whose high-noise and low-noise experts exhibit distinct quantization sensitivities that a single global calibration policy cannot capture. We propose a post.