# Quantize What Counts: More for Keys, Less for Values

arXiv: https://arxiv.org/abs/2502.15075 · HTML: https://mlsanity.com/paper/2502.15075/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in KV cache quantization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 26 of its 48 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Placed in

- Efficient LLM inference and serving / [KV cache quantization](https://mlsanity.com/inference/kv-cache-quantization/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization](https://mlsanity.com/paper/2402.18096/) (2024)
- [WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More](https://mlsanity.com/paper/2402.12065/) (2024)
- [QAQ: Quality Adaptive Quantization for LLM KV Cache](https://mlsanity.com/paper/2403.04643/) (2024)
- [KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference](https://mlsanity.com/paper/2502.04420/) (2025)

## Built on by (most cited first, 10 of 10)

- [Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation](https://mlsanity.com/paper/2510.04265/) (2025)
- [Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?](https://mlsanity.com/paper/2510.12680/) (2025)
- [OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization](https://mlsanity.com/paper/2605.17757/) (2026)
- [InnerQ: Hardware-Aware Tuning-Free Quantization of KV Cache for Large Language Models](https://mlsanity.com/paper/2602.23200/) (2026)
- [Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation](https://mlsanity.com/paper/2604.27201/) (2026)
- [RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory](https://mlsanity.com/paper/2605.06675/) (2026)
- [HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization](https://mlsanity.com/paper/2605.03562/) (2026)
- [Regularize or Localize: When Training-Time KV-Cache Geometry Pays Under Quantization](https://mlsanity.com/paper/2607.17019/) (2026)
- [Behavioral Capacity Certificates for Quantized Language Models](https://mlsanity.com/paper/2609.37887/) (2026)
- [PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference](https://mlsanity.com/paper/2610.19605/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) suffer inference-time memory bottlenecks dominated by the attention Key-Value (KV) cache, which scales with model size and context length. While KV-cache quantization alleviates this cost, bit allocation between keys and values is often tuned heuristically, lacking theoretical grounding and generalizability. This paper proposes two theorems that anchor mixed-precision KV quantization in the intrinsic geometry of Transformer models. First, key projections systematically have larger spectral and Frobenius norms than value matrices, implying higher information density along the key path. Second, for any given memory budget, prioritizing precision for keys over values strictly reduces quantization error and better preserves accuracy. Empirical evaluations across various prominent LLMs and benchmarks show that key-favored allocations (e.g., 4-bit keys, 2-bit values) retain up to 98.3% accuracy compared to uniform allocations (e.g., 4-bit for both), while conserving memory. These results transform bit allocation from ad hoc tuning into a theoretically grounded, geometry-driven design principle for efficient LLM inference. Source code is available at https://github.com/mohsenhariri/spectral-kv.