通过跨请求缓存复用，加速视频生成模型推理
Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse
- 利用多请求间相似性，在去噪过程中复用潜在特征
- 在4步蒸馏模型上实现最高45%的推理加速
- 适合需要高并发视频生成的工业级服务场景
视频扩散变换器（DiT）是高质量视频生成的主流方法，但其迭代去噪过程导致推理成本高昂。现有缓存方法主要利用单个请求内部的相似性来跳过冗余去噪步骤。本文提出Chorus，一种利用跨请求相似性的缓存策略，以加速视频扩散模型的服务。Chorus在工业级4步蒸馏模型上实现了高达45%的加速，而此前的请求内缓存方法在此类模型上无效。该方法采用三阶段缓存策略：第一阶段对相似请求的潜在特征进行全量复用；第二阶段在中间去噪步骤中对特定潜在区域进行跨请求缓存，并结合令牌引导注意力增强，提升生成视频与条件提示之间的语义对齐，从而将全量复用扩展至后期去噪步骤。
原文摘要 · Abstract (English)
Video Diffusion Transformer (DiT) models are a dominant approach for high-quality video generation but suffer from high inference cost due to iterative denoising. Existing caching approaches primarily exploit similarity within the diffusion process of a single request to skip redundant denoising steps. In this paper, we introduce Chorus, a caching approach that leverages similarity across requests to accelerate video diffusion model serving. Chorus achieves up to 45\% speedup on industrial 4-step distilled models, where prior intra-request caching approaches are ineffective. Particularly, Chorus employs a three-stage caching strategy along the denoising process. Stage 1 performs full reuse of latent features from similar requests. Stage 2 exploits inter-request caching in specific latent regions during intermediate denoising steps. This stage is combined with Token-Guided Attention Amplification to improve semantic alignment between the generated video and the conditional prompts, thereby extending the applicability of full reuse to later denoising steps.
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。