Efficient AI
Efficient AI
News
Publications
Light
Dark
Automatic
Kurt Keutzer
Latest
Radial Attention: $\mathcal{O}(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
Cite
×