High-fidelity FP8 quantization for diffusion models (SDXL). HSWQ uses sensitivity and importance analysis instead of naive uniform cast, and offers two modes: standard-compatible (V1) and high-performance scaled (V2).
We extend our deepest respect and gratitude to the Nunchaku Team for their groundbreaking work on SVDQ quantization and for sharing their models with the community. This collection relies heavily on their research and original implementation.
