paper-with-me

Papers

LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation

2025-10-06 · Yang Xiao, Gen Li, Kaiyuan Deng, Yushu Wu, Zheng Zhan, Yanzhi Wang, Xiaolong Ma, Bo Hui arxiv

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 decompose the inference process into the encoding, denoising, and decoding stages, and observe that cache-based acceleration methods often lead to substantial memory surges in the latter two stages. To address this problem, we analyze the characteristics of inference across different stages and propose stage-specific strategies for reducing memory consumption: 1) Asynchronous Cache Swapping. 2) Feature chunk. 3) Slicing latents to decode. At the same time, we ensure that the time overhead introduced by these three strategies remains lower than the acceleration gains themselves. Compared with the baseline, our approach achieves faster inference speed and lower memory usage, while maintaining quality degradation within an acceptable range. The Code is available at https://github.com/NKUShaw/LightCache .

📄 PDF Abstract BibTeX arXiv:2510.05367

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models

2026-05-29 · Jiacheng Lu, Haoyi Zhu, Sipei Yi, Enze Xie 외 arxiv

Interactive video world models generate video chunk by chunk in response to user-controlled camera movements, enabling applications such as real-time game simulation, virtual scene navigation, and embodied AI training. H…

Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation

2026-06-21 · Yitong Li, Junsong Chen, Haopeng Li, Haozhe Liu 외 arxiv

Modern video diffusion models achieve higher generation quality through scaling, but this also increases inference cost. Although many acceleration methods have been proposed, a central challenge is that the most effecti…

Video Generation

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration

2024-12-16 · Wenhao Sun, Rong-Cheng Tu, Jingyi Liao, Zhao Jin 외

Video Diffusion Transformers (DiTs) have demonstrated significant potential for generating high-fidelity videos but are computationally intensive. Existing acceleration methods include distillation, which requires costly…

DenoisingToken Reduction

Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory

2026-05-18 · Jinzhuo Liu, Jiangning Zhang, Wencan Jiang, Yabiao Wang 외 arxiv

Autoregressive video generation has improved rapidly in visual fidelity and interactivity, but it still suffers from long-term inconsistency and memory degradation. Most existing solutions either compress historical fram…

Video Generation

QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation

2025-03-09 · Junyi Wu, Zhiteng Li, Zheng Hui, Yulun Zhang 외

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…

QuantizationVideo Generation