PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models 事件

PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models arXiv:2605.09503v2 Announce Type: replace Abstract: Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challenging in resource-constrained scenarios, such as interactive applications and personal single-GPU usage. Post-training quantization (PTQ) offers a practical solution by compressing pretrained models withou