# FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

arXiv: https://arxiv.org/abs/2503.23367 · HTML: https://mlsanity.com/paper/2503.23367/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Fast autoregressive visual generation, one of 12 directions in Efficient LLM inference and serving.
- Builds on 60 of its 64 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Placed in

- Efficient LLM inference and serving / [Fast autoregressive visual generation](https://mlsanity.com/inference/fast-autoregressive-visual-generation/)

## Builds on (most cited first, 30 of 60)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)

## Built on by (most cited first, 30 of 34)

- [Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities](https://mlsanity.com/paper/2505.02567/) (2025)
- [Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression](https://mlsanity.com/paper/2505.19602/) (2025)
- [Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling](https://mlsanity.com/paper/2504.09261/) (2025)
- [RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration](https://mlsanity.com/paper/2505.18047/) (2025)
- [SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping](https://mlsanity.com/paper/2506.08908/) (2025)
- [MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian Conditioning](https://mlsanity.com/paper/2505.12742/) (2025)
- [PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation](https://mlsanity.com/paper/2603.00976/) (2026)
- [Progressive Supernet Training for Efficient Visual Autoregressive Modeling](https://mlsanity.com/paper/2511.16546/) (2025)
- [ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity Optimization](https://mlsanity.com/paper/2602.22948/) (2026)
- [SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models](https://mlsanity.com/paper/2509.15536/) (2025)
- [SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration](https://mlsanity.com/paper/2602.04361/) (2026)
- [RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space](https://mlsanity.com/paper/2602.20685/) (2026)
- [Multi-Scale Local Speculative Decoding for Image Generation](https://mlsanity.com/paper/2601.05149/) (2026)
- [Markovian Scale Prediction: A New Era of Visual Autoregressive Generation](https://mlsanity.com/paper/2511.23334/) (2025)
- [Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens](https://mlsanity.com/paper/2512.04857/) (2025)
- [FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models](https://mlsanity.com/paper/2512.16483/) (2025)
- [FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis](https://mlsanity.com/paper/2603.07192/) (2026)
- [ActVAR: Activating Mixtures of Weights and Tokens for Efficient Visual Autoregressive Generation](https://mlsanity.com/paper/2511.12893/) (2025)
- [Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis](https://mlsanity.com/paper/2602.01345/) (2026)
- [HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling](https://mlsanity.com/paper/2606.08302/) (2026)
- [Diversity Has Always Been There in Your Visual Autoregressive Models](https://mlsanity.com/paper/2511.17074/) (2025)
- [DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models](https://mlsanity.com/paper/2511.21415/) (2025)
- [StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models](https://mlsanity.com/paper/2603.01757/) (2026)
- [Depth Adaptive Efficient Visual Autoregressive Modeling](https://mlsanity.com/paper/2604.17286/) (2026)
- [Visual Implicit Autoregressive Modeling](https://mlsanity.com/paper/2605.01220/) (2026)
- [ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models](https://mlsanity.com/paper/2605.10045/) (2026)
- [HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling](https://mlsanity.com/paper/2605.14877/) (2026)
- [Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation](https://mlsanity.com/paper/2606.00310/) (2026)
- [MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observations](https://mlsanity.com/paper/2606.23000/) (2026)
- [MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts](https://mlsanity.com/paper/2607.00371/) (2026)

## Abstract (arXiv)

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× 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.