# VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization

arXiv: https://arxiv.org/abs/2603.16435 · HTML: https://mlsanity.com/paper/2603.16435/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 17 Mar 2026.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [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)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models](https://mlsanity.com/paper/2312.05821/) (2023)
- [Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining](https://mlsanity.com/paper/2408.02657/) (2024)
- [MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation](https://mlsanity.com/paper/2209.09002/) (2022)
- [Addressing Representation Collapse in Vector Quantized Models with One Linear Layer](https://mlsanity.com/paper/2411.02038/) (2024)
- [VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers](https://mlsanity.com/paper/2507.01016/) (2025)
- [VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference](https://mlsanity.com/paper/2503.02236/) (2025)
- [Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models](https://mlsanity.com/paper/2602.08984/) (2026)
- [Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache](https://mlsanity.com/paper/2506.11886/) (2025)
- [CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios](https://mlsanity.com/paper/2409.10593/) (2024)

## Built on by (most cited first, 1 of 1)

- [Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression](https://mlsanity.com/paper/2605.27646/) (2026)

## Abstract (arXiv)

The growing context length of Large Language Models (LLMs) enlarges the Key-Value (KV) cache, limiting deployment in resource-limited environments. Prior training-free approaches for KV cache compression typically rely on low-rank approximation or scalar quantization, which fail to simultaneously achieve high compression ratios and high reconstruction fidelity. We propose VQKV, a novel, training-free method introducing vector quantization (VQ) to obtain highly compressed KV representations while preserving high model fidelity, allowing for the representation of thousands of floating-point values with just a few integer indices. As a result, VQKV achieves an 82.8% compression ratio on LLaMA3.1-8B while retaining 98.6% of the baseline performance on LongBench and enabling 4.3x longer generation length on the same memory footprint.