提出细粒度缓存机制，显著加速扩散模型推理
MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers
- 按专家分支而非完整令牌进行跨时间步特征复用
- 在多个DiT-MoE模型上实现最高2.93倍加速，质量不变
- 适合需要高效扩散生成的部署场景
具有专家混合（DiT-MoE）的扩散变换器在稀疏激活下提升了模型容量，但扩散推理仍受制于跨时间步的冗余计算。现有缓存方法主要在令牌级别操作，在DiT-MoE中效果不佳，因为每个令牌更新被分解为多个路由专家分支。我们的分析表明，DiT-MoE中的跨时间步冗余更适合在专家分支层面建模。基于此，我们提出MoECa，一种细粒度缓存框架，实现跨时间步的分支级特征复用。MoECa还引入专家感知的自适应控制与MoE和注意力路径间的同步缓存更新，以维持稳定的中间状态。在多个DiT-MoE模型上的实验表明，该方法在保持生成质量的同时实现了有利的速度-质量权衡，最高可达2.93倍加速。
原文摘要 · Abstract (English)
Diffusion Transformers with Mixture-of-Experts (DiT-MoE) improve model capacity under sparse activation, but diffusion inference is still bottlenecked by redundant computation across timesteps. Existing caching methods mainly operate at the token level, which becomes suboptimal in DiT-MoE because each token update is internally decomposed into multiple routed expert branches. Our analysis shows that cross-timestep redundancy in DiT-MoE is better characterized at the expert-branch level than at the whole-token level. Based on this observation, we propose MoECa, a fine-grained caching framework that performs branch-level feature reuse across timesteps. MoECa further introduces expert-aware adaptive control and synchronized cache updates across MoE and attention paths to maintain stable intermediate states. Experiments on multiple DiT-MoE models show a favorable speed--quality trade-off, with up to 2.93$\times$ speedups while preserving generation quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。