DiTFastAttn: Attention Compression for Diffusion Transformer Models
–Neural Information Processing Systems
Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to the quadratic complexity of self-attention operators. We propose DiTFastAttn, a post-training compression method to alleviate the computational bottleneck of DiT.
Neural Information Processing Systems
Dec-27-2025, 15:54:28 GMT
- Country:
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (1.00)
- Workflow (0.93)
- Research Report
- Industry:
- Information Technology (0.46)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Natural Language (1.00)
- Representation & Reasoning (0.93)
- Vision (1.00)
- Information Technology > Artificial Intelligence