quadratic time complexity
- Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective
- Fast attention mechanisms: a tale of parallelism
- SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
- Shapley-Based Data Valuation for Weighted $k$-Nearest Neighbors
- dKV-Cache: The Cache for Diffusion Language Models