# KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference

arXiv: https://arxiv.org/abs/2502.04420 · HTML: https://mlsanity.com/paper/2502.04420/

## Key facts

- Cited by 40 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 61 of its 69 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Placed in

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

## Builds on (most cited first, 30 of 61)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [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)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [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)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)

## Built on by (most cited first, 30 of 40)

- [PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs](https://mlsanity.com/paper/2505.18610/) (2025)
- [Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity](https://mlsanity.com/paper/2505.21411/) (2025)
- [Quantize What Counts: More for Keys, Less for Values](https://mlsanity.com/paper/2502.15075/) (2025)
- [Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost](https://mlsanity.com/paper/2511.18643/) (2025)
- [What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study](https://mlsanity.com/paper/2601.14888/) (2026)
- [Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs](https://mlsanity.com/paper/2604.04722/) (2026)
- [SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention](https://mlsanity.com/paper/2502.15304/) (2025)
- [KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache](https://mlsanity.com/paper/2506.08018/) (2025)
- [Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis](https://mlsanity.com/paper/2601.21709/) (2026)
- [VeriCache: Turning Lossy KV Cache into Lossless LLM Inference](https://mlsanity.com/paper/2605.17613/) (2026)
- [KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference](https://mlsanity.com/paper/2512.01953/) (2025)
- [Towards Efficient Agents: A Co-Design of Inference Architecture and System](https://mlsanity.com/paper/2512.18337/) (2025)
- [RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache](https://mlsanity.com/paper/2605.08317/) (2026)
- [A Simple Plug-in for Improving Eviction-Based KV Cache Compression](https://mlsanity.com/paper/2605.23258/) (2026)
- [Beyond Speedup -- Utilizing KV Cache for Sampling and Reasoning](https://mlsanity.com/paper/2601.20326/) (2026)
- [Don't be so Stief! Learning KV Cache low-rank approximation over the Stiefel manifold](https://mlsanity.com/paper/2601.21686/) (2026)
- [RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory](https://mlsanity.com/paper/2605.06675/) (2026)
- [Search Your Block Floating Point Scales!](https://mlsanity.com/paper/2605.12464/) (2026)
- [ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs](https://mlsanity.com/paper/2602.07721/) (2026)
- [Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats](https://mlsanity.com/paper/2602.12635/) (2026)
- [PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization](https://mlsanity.com/paper/2607.16184/) (2026)
- [Detecting a Route Flip Is Easier Than Knowing Whether to Fix It: Causal Route-Mediated Damage in Quantized Mixture-of-Experts](https://mlsanity.com/paper/2608.11212/) (2026)
- [A Unified Sparse Attention via Multi-Granularity Compression](https://mlsanity.com/paper/2512.14082/) (2025)
- [Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer Refinement](https://mlsanity.com/paper/2609.25916/) (2026)
- [CompKV: Compensation-Aware KV Selection for Long-Context LLM Inference](https://mlsanity.com/paper/2609.26300/) (2026)
- [KV-Kaizen: Learning Context-Adaptive Cache Compression Choices](https://mlsanity.com/paper/2609.37988/) (2026)
- [Monte Carlo Estimation for KV Cache Eviction](https://mlsanity.com/paper/2610.07643/) (2026)
- [HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization](https://mlsanity.com/paper/2605.03562/) (2026)
- [Minimal-Intervention KV Retention via Set-Conditioned Diversity](https://mlsanity.com/paper/2605.14292/) (2026)
- [Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression](https://mlsanity.com/paper/2605.27646/) (2026)

## Abstract (arXiv)

KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness. However, current methods have three unsolved issues: overlooking layer-wise sensitivity to KV cache quantization, high overhead of online fine-grained decision-making, and low flexibility to different LLMs and constraints. Therefore, we theoretically analyze the inherent correlation of layer-wise transformer attention patterns to KV cache quantization errors and study why key cache is generally more important than value cache for quantization error reduction. We further propose a simple yet effective framework KVTuner to adaptively search for the optimal hardware-friendly layer-wise KV quantization precision pairs for coarse-grained KV cache with multi-objective optimization and directly utilize the offline searched configurations during online inference. To reduce the computational cost of offline calibration, we utilize the intra-layer KV precision pair pruning and inter-layer clustering to reduce the search space. Experimental results show that we can achieve nearly lossless 3.25-bit mixed precision KV cache quantization for LLMs like Llama-3.1-8B-Instruct and 4.0-bit for sensitive models like Qwen2.5-7B-Instruct on mathematical reasoning tasks. The maximum inference throughput can be improved by 21.25% compared with KIVI-KV8 quantization over various context lengths. Our code and searched configurations are available at https://github.com/cmd2001/KVTuner.