paper-with-me

Papers

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

2025-03-30 · Hang Guo, Yawei Li, Taolin Zhang, Jiangshan Wang, Tao Dai, Shu-Tao Xia, Luca Benini

Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale step, leading to the complexity and runtime scaling dramatically with image resolution. To address this challenge, we propose FastVAR, a post-training acceleration method for efficient resolution scaling with VARs. Our key finding is that the majority of latency arises from the large-scale step where most tokens have already converged. Leveraging this observation, we develop the cached token pruning strategy that only forwards pivotal tokens for scale-specific modeling while using cached tokens from previous scale steps to restore the pruned slots. This significantly reduces the number of forwarded tokens and improves the efficiency at larger resolutions. Experiments show the proposed FastVAR can further speedup FlashAttention-accelerated VAR by 2.7$\times$ with negligible performance drop of <1%. We further extend FastVAR to zero-shot generation of higher resolution images. In particular, FastVAR can generate one 2K image with 15GB memory footprints in 1.5s on a single NVIDIA 3090 GPU. Code is available at https://github.com/csguoh/FastVAR.

📄 PDF Abstract BibTeX arXiv:2503.23367

Code (1)

csguoh/fastvar 공식 구현 pytorch

Tasks

2kGPU

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity Optimization

2026-02-26 · Jiayu Chen, Ruoyu Lin, Zihao Zheng, Jingxin Li 외 arxiv

Visual Autoregressive(VAR) models enhance generation quality but face a critical efficiency bottleneck in later stages. In this paper, we present a novel optimization framework for VAR models that fundamentally differs f…

Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens

2025-12-04 · Ziran Qin, Youru Lv, Mingbao Lin, Zeren Zhang 외 arxiv

Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image generation suffers from severe memory bottl…

Text-to-Image Generation

Randomized Autoregressive Visual Generation

2024-11-01 · Qihang Yu, Ju He, Xueqing Deng, Xiaohui Shen 외

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling f…

Image GenerationLanguage ModelingLanguage Modelling

Dynamic Variational Autoencoders for Visual Process Modeling

2018-03-20 · Alexander Sagel, Hao Shen

This work studies the problem of modeling visual processes by leveraging deep generative architectures for learning linear, Gaussian representations from observed sequences. We propose a joint learning framework, combini…

Compiler-First State Space Duality and Portable $O(1)$ Autoregressive Caching for Inference

2026-03-10 · Cosmo Santoni, Anmol Thapar arxiv

High-throughput Mamba-2 inference is usually tied to fused CUDA and Triton kernels, limiting portability across accelerator backends. We show that the state space duality (SSD) recurrence has a compiler-friendly structur…