🏢 MIT
SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
·4041 words·19 mins
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 MIT
SVDQuant boosts 4-bit diffusion models by absorbing outliers via low-rank components, achieving 3.5x memory reduction and 3x speedup on 12B parameter models.