7 papers
HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction
Luxi Lin, Shuang Peng, Rui Ma +7
We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC). Despite the strong performance of DeepSeek-V4's native Mul…
S2O: Early Stopping for Sparse Attention via Online Permutation
Yu Zhang, Songwei Liu, Chenqian Yan +4
Attention scales quadratically with sequence length, fundamentally limiting long-context inference. Existing block-granularity sparsification can reduce latency, but coarse blocks…
Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion
Songwei Liu, Chao Zeng, Chenqian Yan +4
Diffusion models have transformed image synthesis by establishing unprecedented quality and creativity benchmarks. Nevertheless, their large-scale deployment faces challenges due t…
TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
Haowei Zhu, Tingxuan Huang, Xing Wang +7
Diffusion models achieve strong generative performance but remain slow at inference due to the need for repeated full-model denoising passes. We present Token-Adaptive Predictor (T…
ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
Xurui Peng, Chenqian Yan, Hong Liu +6
Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process. While feature caching offers a promising acceleration strategy…
GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference
Chao Zeng, Songwei Liu, Shu Yang +3
Model compression has emerged as a mainstream solution to reduce memory usage and computational overhead. This paper presents Group Quantization and Sparse Acceleration (GQSA), a n…