# Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning

arXiv: https://arxiv.org/abs/2410.19258 · HTML: https://mlsanity.com/paper/2410.19258/

## Key facts

- Cited by 97 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 36 of its 40 references that are in the map.
- First posted on arXiv 25 Oct 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference](https://mlsanity.com/paper/2407.11550/) (2024)
- [Retrieval Head Mechanistically Explains Long-Context Factuality](https://mlsanity.com/paper/2404.15574/) (2024)
- [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [In-context Autoencoder for Context Compression in a Large Language Model](https://mlsanity.com/paper/2307.06945/) (2023)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [A Fast Post-Training Pruning Framework for Transformers](https://mlsanity.com/paper/2204.09656/) (2022)
- [A Critical Evaluation of Evaluations for Long-form Question Answering](https://mlsanity.com/paper/2305.18201/) (2023)
- [RazorAttention: Efficient KV Cache Compression Through Retrieval Heads](https://mlsanity.com/paper/2407.15891/) (2024)
- [Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2402.18154/) (2024)
- [ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition](https://mlsanity.com/paper/2402.15220/) (2024)

## Built on by (most cited first, 30 of 97)

- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding](https://mlsanity.com/paper/2506.15745/) (2025)
- [StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding](https://mlsanity.com/paper/2508.15717/) (2025)
- [R-KV: Redundancy-aware KV Cache Compression for Reasoning Models](https://mlsanity.com/paper/2505.24133/) (2025)
- [CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective](https://mlsanity.com/paper/2502.03805/) (2025)
- [StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression](https://mlsanity.com/paper/2511.07278/) (2025)
- [Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression](https://mlsanity.com/paper/2505.19602/) (2025)
- [ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models](https://mlsanity.com/paper/2510.01290/) (2025)
- [Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs](https://mlsanity.com/paper/2503.00979/) (2025)
- [Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning](https://mlsanity.com/paper/2505.13866/) (2025)
- [ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration](https://mlsanity.com/paper/2505.24357/) (2025)
- [LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning](https://mlsanity.com/paper/2506.15969/) (2025)
- [Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling](https://mlsanity.com/paper/2504.09261/) (2025)
- [FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration](https://mlsanity.com/paper/2502.01068/) (2025)
- [Taming the Fragility of KV Cache Eviction in LLM Inference](https://mlsanity.com/paper/2510.13334/) (2025)
- [Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models](https://mlsanity.com/paper/2510.20707/) (2025)
- [Streaming Attention Approximation via Discrepancy Theory](https://mlsanity.com/paper/2502.07861/) (2025)
- [More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression](https://mlsanity.com/paper/2412.12706/) (2024)
- [OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2510.07651/) (2025)
- [Which Heads Matter for Reasoning? RL-Guided KV Cache Compression](https://mlsanity.com/paper/2510.08525/) (2025)
- [HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading](https://mlsanity.com/paper/2502.12574/) (2025)
- [KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference](https://mlsanity.com/paper/2504.09936/) (2025)
- [UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression](https://mlsanity.com/paper/2509.15763/) (2025)
- [Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference](https://mlsanity.com/paper/2505.22913/) (2025)
- [G-KV: Decoding-Time KV Cache Eviction with Global Attention](https://mlsanity.com/paper/2512.00504/) (2025)
- [RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention](https://mlsanity.com/paper/2606.06256/) (2026)
- [SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning](https://mlsanity.com/paper/2508.15212/) (2025)
- [Predicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction](https://mlsanity.com/paper/2602.08585/) (2026)
- [MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering](https://mlsanity.com/paper/2605.22269/) (2026)

## Abstract (arXiv)

Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior work has shown that not all tokens are equally important for text generation, proposing layer-level KV cache compression to selectively retain key information. Recognizing the distinct roles of attention heads in generation, we propose HeadKV, a head-level KV cache compression method, and HeadKV-R2, which leverages a novel contextual reasoning ability estimation for compression. Our approach operates at the level of individual heads, estimating their importance for contextual QA tasks that require both retrieval and reasoning capabilities. Extensive experiments across diverse benchmarks (LongBench, LooGLE), model architectures (e.g., Llama-3-8B-Instruct, Mistral-7B-Instruct), and long-context abilities tests demonstrate that our head-level KV cache compression significantly outperforms strong baselines, particularly in low-resource settings (KV size = 64 & 128). Notably, our method retains just 1.5% of the KV cache while achieving 97% of the performance of the full KV cache on the contextual question answering benchmark. Codes are available at https://github.com/FYYFU/HeadKV