# AMS-KV: Adaptive KV Caching in Multi-Scale Visual Autoregressive Transformers

arXiv: https://arxiv.org/abs/2511.16047 · HTML: https://mlsanity.com/paper/2511.16047/

## Key facts

- Cited by 2 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 34 of its 46 references that are in the map.
- First posted on arXiv 20 Nov 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 34)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (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)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis](https://mlsanity.com/paper/2412.04431/) (2024)
- [Compact Language Models via Pruning and Knowledge Distillation](https://mlsanity.com/paper/2407.14679/) (2024)
- [You Only Cache Once: Decoder-Decoder Architectures for Language Models](https://mlsanity.com/paper/2405.05254/) (2024)
- [Reducing Transformer Key-Value Cache Size with Cross-Layer Attention](https://mlsanity.com/paper/2405.12981/) (2024)
- [VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling](https://mlsanity.com/paper/2408.01181/) (2024)
- [SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE](https://mlsanity.com/paper/2411.16856/) (2024)
- [STAR: Scale-wise Text-conditioned AutoRegressive image generation](https://mlsanity.com/paper/2406.10797/) (2024)

## Built on by (most cited first, 2 of 2)

- [From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models](https://mlsanity.com/paper/2603.04592/) (2026)
- [HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling](https://mlsanity.com/paper/2605.14877/) (2026)

## Abstract (arXiv)

Visual autoregressive modeling (VAR) via next-scale prediction has emerged as a scalable image generation paradigm. While Key and Value (KV) caching in large language models (LLMs) has been extensively studied, next-scale prediction presents unique challenges, and KV caching design for next-scale based VAR transformers remains largely unexplored. A major bottleneck is the excessive KV memory growth with the increasing number of scales-severely limiting scalability. Our systematic investigation reveals that: (1) Attending to tokens from local scales significantly contributes to generation quality (2) Allocating a small amount of memory for the coarsest scales, termed as condensed scales, stabilizes multi-scale image generation (3) Strong KV similarity across finer scales is predominantly observed in cache-efficient layers, whereas cache-demanding layers exhibit weaker inter-scale similarity. Based on the observations, we introduce AMS-KV, a scale-adaptive KV caching policy for next-scale prediction in VAR models. AMS-KV prioritizes storing KVs from condensed and local scales, preserving the most relevant tokens to maintain generation quality. It further optimizes KV cache utilization and computational efficiency identifying cache-demanding layers through inter-scale similarity analysis. Compared to the vanilla next-scale prediction-based VAR models, AMS-KV reduces KV cache usage by up to 84.83% and self-attention latency by 60.48%. Moreover, when the baseline VAR-d30 model encounters out-of-memory failures at a batch size of 128, AMS-KV enables stable scaling to a batch size of 256 with improved throughput.