# LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization

arXiv: https://arxiv.org/abs/2411.17178 · HTML: https://mlsanity.com/paper/2411.17178/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 21 references that are in the map.
- First posted on arXiv 26 Nov 2024.

## Builds on (most cited first, 20 of 20)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization](https://mlsanity.com/paper/2111.12293/) (2021)
- [Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT](https://mlsanity.com/paper/2406.18583/) (2024)
- [ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation](https://mlsanity.com/paper/2406.02540/) (2024)
- [DiTFastAttn: Attention Compression for Diffusion Transformer Models](https://mlsanity.com/paper/2406.08552/) (2024)

## Built on by (most cited first, 17 of 17)

- [Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression](https://mlsanity.com/paper/2505.19602/) (2025)
- [TR-DQ: Time-Rotation Diffusion Quantization](https://mlsanity.com/paper/2503.06564/) (2025)
- [Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling](https://mlsanity.com/paper/2504.09261/) (2025)
- [SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping](https://mlsanity.com/paper/2506.08908/) (2025)
- [PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models](https://mlsanity.com/paper/2601.21238/) (2026)
- [AMS-KV: Adaptive KV Caching in Multi-Scale Visual Autoregressive Transformers](https://mlsanity.com/paper/2511.16047/) (2025)
- [Markovian Scale Prediction: A New Era of Visual Autoregressive Generation](https://mlsanity.com/paper/2511.23334/) (2025)
- [FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models](https://mlsanity.com/paper/2512.16483/) (2025)
- [FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design](https://mlsanity.com/paper/2505.16335/) (2025)
- [Dynamic Mixture-of-Experts for Visual Autoregressive Model](https://mlsanity.com/paper/2510.08629/) (2025)
- [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)
- [Shift-and-Sum Quantization for Visual Autoregressive Models](https://mlsanity.com/paper/2606.16131/) (2026)
- [Depth Adaptive Efficient Visual Autoregressive Modeling](https://mlsanity.com/paper/2604.17286/) (2026)
- [HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling](https://mlsanity.com/paper/2605.14877/) (2026)
- [HGA-Quant: Heterogeneity-Aware Quantization for AutoRegressive Visual Generation Models](https://mlsanity.com/paper/2610.15297/) (2026)

## Abstract (arXiv)

Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models. However, current AR-based visual generation models require substantial computational resources, limiting their applicability on resource-constrained devices. To address this issue, we conducted analysis and identified significant redundancy in three dimensions of the VAR model: (1) the attention map, (2) the attention outputs when using classifier free guidance, and (3) the data precision. Correspondingly, we proposed efficient attention mechanism and low-bit quantization method to enhance the efficiency of VAR models while maintaining performance. With negligible performance lost (less than 0.056 FID increase), we could achieve 85.2% reduction in attention computation, 50% reduction in overall memory and 1.5x latency reduction. To ensure deployment feasibility, we developed efficient training-free compression techniques and analyze the deployment feasibility and efficiency gain of each technique.