QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification

Documenti analoghi

• S$^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
  di: Feng, Weilun, et al.
  Pubblicazione: (2025)
• Quantized Visual Geometry Grounded Transformer
  di: Feng, Weilun, et al.
  Pubblicazione: (2025)
• Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers
  di: Feng, Weilun, et al.
  Pubblicazione: (2025)
• MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation
  di: Feng, Weilun, et al.
  Pubblicazione: (2025)
• MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models
  di: Feng, Weilun, et al.
  Pubblicazione: (2024)