Related papers: LayerCache: Exploiting Layer-wise Velocity Heterog…
We present MeanCache, a training-free caching framework for efficient Flow Matching inference. Existing caching methods reduce redundant computation but typically rely on instantaneous velocity information (e.g., feature caching), which…
Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing caching methods…
Transformer-based language models have achieved remarkable performance across a wide range of tasks, yet their high inference latency poses a significant challenge for real-timeand large-scale deployment. While existing caching…
As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising. Previous methods speed up the models by caching and reusing model outputs at uniformly…
Diffusion Transformers have recently demonstrated unprecedented generative capabilities for various tasks. The encouraging results, however, come with the cost of slow inference, since each denoising step requires inference on a transformer…
Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion…
Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. However, this sequential generation process is notoriously slow.…
Graphics rendering applications increasingly leverage neural networks in tasks such as denoising, supersampling, and frame extrapolation to improve image quality while maintaining frame rates. The temporal coherence inherent in these tasks…
Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…
Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising process. While existing caching techniques can accelerate…
We address LLM serving workloads where repeated requests share a common solution structure but differ in localized constraints, such as output schema, variable names, or numeric constants. Prior caching approaches typically reuse either…
Switching, routing, and security functions are the backbone of packet processing networks. Fast and efficient processing of packets requires maintaining the state of a large number of transient network connections. In particular, modern…
Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process. While feature caching offers a promising acceleration strategy by reusing intermediate outputs across timesteps, naive…
Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally expensive. Existing caching methods accelerate sampling by skipping timesteps, yet their…
Existing cache-based acceleration methods for video diffusion models primarily skip early or mid denoising steps, which often leads to structural discrepancies relative to full-timestep generation and can hinder instruction following and…
Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance. However, the enhanced capabilities of DiTs come with significant drawbacks,…
Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…
Diffusion models are a strong backbone for visual generation, but their inherently sequential denoising process leads to slow inference. Previous methods accelerate sampling by caching and reusing intermediate outputs based on feature…
Diffusion models deliver high-fidelity synthesis but remain slow due to iterative sampling. We empirically observe there exists feature invariance in deterministic sampling, and present InvarDiff, a training-free acceleration method that…
Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we…