Skip to main content

🏢 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.