4 papers · 1 filter
From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
Xichen Ye, Yifan Wu, Zhikang Xie +3
Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead. While cache-based acceleration has emerged as a promising s…
OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference
Zhikang Xie, Xichen Ye, Yifan Wu +5
Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising. While cache-based strategies accelerate inference by reusing intermediate f…
Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning
Yifan Wu, Yiqi Wang, Xichen Ye +5
Knowledge Distillation (KD) is widely used to obtain compact models for efficient inference in resource-constrained environments. Yet the computational overhead of the distillation…
Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization
Weilin Wan, Jingtao Han, Weizhong Zhang +2
Scaling laws govern macroscopic resource allocation for LLMs, yet precise architectural configurations for Mixture-of-Experts (MoE) models remain guided by heuristics. Existing MoE…