8 papers
MXAttention: Data-Free Optimal Scaling and Pre-Normalization Quantization for MXFP4 Attention
Jianlin Yu, Jing Lin, Linghui Kong +13
The quadratic cost of attention is a major bottleneck in diffusion-based video generation models. MXFP4 attention provides a promising path toward efficient inference, but direct M…
StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention Distillation
Guangda Liu, Yiquan Wang, Chengwei Li +6
Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, mod…
RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention
Aiyue Chen, Yaofu Liu, Junjian Huang +6
In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applicati…
FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
Guangda Liu, Chengwei Li, Zhenyu Ning +5
Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant depl…
Timeripple: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space
Wenxuan Miao, Yulin Sun, Aiyue Chen +8
The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly bas…
DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
Yuantian Shao, Yuanteng Chen, Peisong Wang +5
Quantization plays a crucial role in accelerating the inference of large-scale models, and rotational matrices have been shown to effectively improve quantization performance by sm…