OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
OrbitQuant enables efficient post-training quantization for diffusion transformers by using a normalized rotated basis that eliminates the need for recalibration across different t…
Hugging Face · Daily Papers
·Donghyun Lee, Jitesh Chavan
·
·▲ 29 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Donghyun Lee, Jitesh Chavan, Duy Nguyen, Sam Huang, Liming Jiang, Priyadarshini Panda
- 29 upvotes da comunidade
- Temas: diffusion transformers, post-training quantization, weight-activation quantizer, normalized rotated basis, randomized permuted block-Hadamard, Lloyd-Max codebook
Resumo
Resumo original (em inglês), extraído do paper:
OrbitQuant enables efficient post-training quantization for diffusion transformers by using a normalized rotated basis that eliminates the need for recalibration across different timesteps and modalities.Onde ler
// relacionados
Leia também
Editorial
EditBridge: edição de imagem em 4K sem inventar o que não estava lá
Blog
Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
Blog
DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization
Blog