Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse

• URL: http://arxiv.org/abs/2604.04451v1
• Date: Mon, 06 Apr 2026 05:55:13 GMT
• Title: Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse
• Abstract summary: Chorus is a caching approach that leverages similarity across requests to accelerate video diffusion model serving.<n> Chorus achieves up to 45% speedup on industrial 4-step distilled models.
• Score: 19.120308047100057
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Motion-Aware Caching for Efficient Autoregressive Video Generation [73.27762884730272]
  MotionCache exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics.<n>Experiments on state-of-the-art models like SkyReels-V2 and MAGI-1 demonstrate that MotionCache achieves significant speedups.
  arXiv  Detail & Related papers  (2026-05-03T05:49:27Z)
• Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep [37.62908191585867]
  HetCache is a training-free diffusion acceleration framework for video-to-video (MV2V) generation and editing.<n>It reduces redundant attention operations while maintaining editing consistency and fidelity.<n> Experiments show that HetCache achieves a noticeable acceleration, including a 2.67$times$ latency speedup and FLOPs reduction over commonly used foundation models.
  arXiv  Detail & Related papers  (2026-03-25T12:53:31Z)
• WorldCache: Content-Aware Caching for Accelerated Video World Models [50.7543797435026]
  We present textbfWorldCache, a Perception-Constrained Dynamic CaCache framework.<n>WorldCache improves both when and how to reuse features.<n>On Cosmos-2.5-2B evaluated on PAI-Bench, WorldCache achieves textbf$2.3times$ inference speedup while preserving textbf99.4% of baseline quality.
  arXiv  Detail & Related papers  (2026-03-23T17:59:54Z)
• Streaming Autoregressive Video Generation via Diagonal Distillation [50.13573884115673]
  Autoregressive models offer a natural framework for sequential frame synthesis but require heavy computation to achieve high fidelity.<n>We propose Diagonal Distillation to exploit temporal information across both video chunks and denoising steps.<n>Our method generates a 5-second video in 2.61 seconds (up to 31 FPS), achieving a 277.3x speedup over the undistilled model.
  arXiv  Detail & Related papers  (2026-03-10T10:45:24Z)
• SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching [75.02865981328509]
  Caching reduces computation by reusing previously computed model outputs across timesteps.<n>We propose Sensitivity-Aware Caching (SenCache), a dynamic caching policy that adaptively selects caching timesteps on a per-sample basis.<n>SenCache achieves better visual quality than existing caching methods under similar computational budgets.
  arXiv  Detail & Related papers  (2026-02-27T17:36:09Z)
• Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation [50.04968365065964]
  Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference.<n>We introduce Lightning-fast Caching-based Parallel denoising prediction (LightningCP)<n>We also propose Decoupled Foreground Attention (DFA) to further accelerate attention computations.
  arXiv  Detail & Related papers  (2025-08-25T02:58:39Z)
• TaoCache: Structure-Maintained Video Generation Acceleration [4.594224594572109]
  We present TaoCache, a training-free, plug-and-play caching strategy for video diffusion models.<n>It adopts a fixed-point perspective to predict the model's noise output and is specifically effective in late denoising stages.
  arXiv  Detail & Related papers  (2025-08-12T14:40:36Z)
• Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching [57.7533917467934]
  EasyCache is a training-free acceleration framework for video diffusion models.<n>We conduct comprehensive studies on various large-scale video generation models, including OpenSora, Wan2.1, and HunyuanVideo.<n>Our method achieves leading acceleration performance, reducing inference time by up to 2.1-3.3$times$ compared to the original baselines.
  arXiv  Detail & Related papers  (2025-07-03T17:59:54Z)
• FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion [22.207275433870937]
  Diffusion language models offer parallel token generation and inherent bidirectionality.<n>State-of-the-art diffusion models (e.g., Dream 7B, LLaDA 8B) suffer from slow inference.<n>We introduce Guided Diffusion, a training-free method that uses a lightweight pretrained autoregressive model to supervise token unmasking.
  arXiv  Detail & Related papers  (2025-05-27T17:39:39Z)
• Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models [41.11005178050448]
  ProfilingDiT is a novel adaptive caching strategy that explicitly disentangles foreground and background-focused blocks.<n>Our framework achieves significant acceleration while maintaining visual fidelity across comprehensive quality metrics.
  arXiv  Detail & Related papers  (2025-04-04T03:30:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.