Byeongju Kim, Hoonki Lee, Byungjun Kim, Inyul Ra, Yongjin Kim, Yongseong Lee, Sangyeob Kim
原文摘要
Despite growing interest in on-device LLM deployment, large-scale Mixture-of-Experts (MoE) models remain impractical on resource-constrained devices, as sparse expert activation still requires all expert weights to be memory-resident. To address this, we identify three key observations for on-device MoE inference: (a) cache hit rates are fundamentally bounded even under Belady's optimal policy; (b) these bounds are insufficient for low-latency on-device inference; and (c) prior cache-aware routing based on binary cache presence can induce routing instability. Based on these insights, we propose CECAR (Cache & Expert Co-Aware Routing), a MoE inference system that jointly considers expert routing and cache management. Unlike prior cache-aware routing methods, CECAR uses an ML-based cache policy to predict the expected reuse distance of each expert and prioritizes routing and execution toward experts with smaller predicted reuse distances. On the Qwen3-30B-A3B model, CECAR achieves 12.5 tokens/s on a consumer-grade GPU with only 16 GB of VRAM, where non-resident experts are fetched from SSD, delivering a 4.5x speedup over conventional MoE inference and exceeding the decode speed of baselines that keep the entire model fully resident in DRAM. Code is available at https://github.com/hoonki2002/CECAR.
Despite recent advancements in Text-to-Video (T2V) synthesis, generating high-fidelity and dynamic motion remains a significant challenge. Existing methods primarily rely on Classifier-Free Guidance (CFG), but standard CFG treats all semantic dimensions uniformly and provides no mechanism to selectively resolve ambiguity along the motion axis. To address this, we propose MotionCFG, a training-free approach that introduces selective guidance along the motion subspace of the condition embedding. Specifically, we construct a motion-perturbed negative condition by injecting Gaussian noise into motion-related embeddings, and steer generation away from it to selectively amplify motion intent. We show theoretically that this procedure implicitly approximates Semantic Laplacian Sharpening, a second-order correction that suppresses motion-ambiguous regions of the score landscape and amplifies well-resolved dynamic peaks. Combined with a piecewise guidance schedule that confines intervention to the early denoising steps, MotionCFG consistently improves motion dynamics across state-of-the-art T2V frameworks with negligible overhead. We further demonstrate that this Laplacian sharpening principle generalizes beyond motion, effectively steering complex, non-linear concepts such as precise object numerosity that are typically difficult to modulate via standard text-based guidance. Our project page is available at https://motion-cfg.vercel.app/.