# Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores

arXiv: https://arxiv.org/abs/2507.08143 · HTML: https://mlsanity.com/paper/2507.08143/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 34 of its 47 references that are in the map.
- First posted on arXiv 10 Jul 2025.

## Placed in

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

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [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)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [Jamba: A Hybrid Transformer-Mamba Language Model](https://mlsanity.com/paper/2403.19887/) (2024)
- [MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention](https://mlsanity.com/paper/2407.02490/) (2024)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads](https://mlsanity.com/paper/2410.10819/) (2024)
- [Prompt Cache: Modular Attention Reuse for Low-Latency Inference](https://mlsanity.com/paper/2311.04934/) (2023)
- [InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management](https://mlsanity.com/paper/2406.19707/) (2024)
- [Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference](https://mlsanity.com/paper/2407.11550/) (2024)
- [CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion](https://mlsanity.com/paper/2405.16444/) (2024)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Transformers are Multi-State RNNs](https://mlsanity.com/paper/2401.06104/) (2024)
- [RazorAttention: Efficient KV Cache Compression Through Retrieval Heads](https://mlsanity.com/paper/2407.15891/) (2024)
- [KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization](https://mlsanity.com/paper/2405.03917/) (2024)
- [Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters](https://mlsanity.com/paper/2406.12335/) (2024)
- [LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference](https://mlsanity.com/paper/2407.14057/) (2024)
- [SCBench: A KV Cache-Centric Analysis of Long-Context Methods](https://mlsanity.com/paper/2412.10319/) (2024)
- [KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments](https://mlsanity.com/paper/2504.15364/) (2025)
- [ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching](https://mlsanity.com/paper/2403.17312/) (2024)

## Built on by (most cited first, 17 of 17)

- [KVzap: Fast, Adaptive, and Faithful KV Cache Pruning](https://mlsanity.com/paper/2601.07891/) (2026)
- [Learning to Evict from Key-Value Cache](https://mlsanity.com/paper/2602.10238/) (2026)
- [Multi-Vector Index Compression in Any Modality](https://mlsanity.com/paper/2602.21202/) (2026)
- [KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs](https://mlsanity.com/paper/2604.13226/) (2026)
- [Value-Aware Stochastic KV Cache Eviction for Reasoning Models](https://mlsanity.com/paper/2606.03928/) (2026)
- [Still: Amortized KV Cache Compaction in a Single Forward Pass](https://mlsanity.com/paper/2606.07878/) (2026)
- [WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization](https://mlsanity.com/paper/2607.28699/) (2026)
- [Rethinking LoRA Memory Through the Lens of KV Cache Compression](https://mlsanity.com/paper/2606.05698/) (2026)
- [Trust the Mass: Forced Weights in KV-Cache Eviction](https://mlsanity.com/paper/2608.25230/) (2026)
- [ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction](https://mlsanity.com/paper/2609.36835/) (2026)
- [EchoPress: Query-Agnostic KV Cache Pruning via Virtual Context Reconstruction](https://mlsanity.com/paper/2610.00412/) (2026)
- [KV2: A Self-Refining KV Cache](https://mlsanity.com/paper/2610.03198/) (2026)
- [How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit](https://mlsanity.com/paper/2607.11942/) (2026)
- [Emergent Structure in the Marginal Attention Space of Language Models](https://mlsanity.com/paper/2610.03109/) (2026)
- [The Optimization Landscape of Learning Compacted Context Models](https://mlsanity.com/paper/2610.05885/) (2026)
- [Generative Adversarial Loops](https://mlsanity.com/paper/2610.11458/) (2026)
- [Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read](https://mlsanity.com/paper/2610.12133/) (2026)

## Abstract (arXiv)

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token importance. We show that Compactor can achieve the same performance as competing methods while retaining 20% fewer tokens in both synthetic and real-world context tasks, while being more task-robust. We further introduce a procedure for context-calibrated compression: inferring the maximum compression a given context supports before significant performance loss. Using context-calibrated compression, we show that Compactor achieves full KV performance on Longbench while reducing the KV memory burden by 68%, on average. To demonstrate the efficacy and generalizability of our approach, we apply Compactor to 27 synthetic and real-world tasks from RULER and Longbench, with models from both the Qwen 2.5 and Llama 3.1 families. Finally, we release compactor-vllm, an inference engine and suite of optimized Triton kernels designed to efficiently support the sparse, non-contiguous memory access patterns inherent to compressed KV caches. This work demonstrates that Compactor offers a practical, high-performance solution for alleviating the memory bottleneck in modern LLM deployment.