# SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation

arXiv: https://arxiv.org/abs/2412.13649 · HTML: https://mlsanity.com/paper/2412.13649/

## Key facts

- Cited by 20 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 29 of its 40 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Placed in

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

## Builds on (most cited first, 29 of 29)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [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)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (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)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [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)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (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)
- [Retrieval Head Mechanistically Explains Long-Context Factuality](https://mlsanity.com/paper/2404.15574/) (2024)
- [InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://mlsanity.com/paper/2402.04617/) (2024)
- [MagicPIG: LSH Sampling for Efficient LLM Generation](https://mlsanity.com/paper/2410.16179/) (2024)
- [Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption](https://mlsanity.com/paper/2407.18003/) (2024)
- [Loki: Low-rank Keys for Efficient Sparse Attention](https://mlsanity.com/paper/2406.02542/) (2024)
- [ThinK: Thinner Key Cache by Query-Driven Pruning](https://mlsanity.com/paper/2407.21018/) (2024)
- [ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression](https://mlsanity.com/paper/2412.03213/) (2024)
- [KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches](https://mlsanity.com/paper/2407.01527/) (2024)
- [Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs](https://mlsanity.com/paper/2404.10308/) (2024)
- [SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding](https://mlsanity.com/paper/2406.18200/) (2024)

## Built on by (most cited first, 20 of 20)

- [LightThinker: Thinking Step-by-Step Compression](https://mlsanity.com/paper/2502.15589/) (2025)
- [Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression](https://mlsanity.com/paper/2502.01941/) (2025)
- [ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking](https://mlsanity.com/paper/2510.24698/) (2025)
- [Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation](https://mlsanity.com/paper/2507.06607/) (2025)
- [Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference](https://mlsanity.com/paper/2505.22913/) (2025)
- [Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs](https://mlsanity.com/paper/2604.04722/) (2026)
- [GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction](https://mlsanity.com/paper/2509.00388/) (2025)
- [EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices](https://mlsanity.com/paper/2503.22196/) (2025)
- [LightThinker++: From Reasoning Compression to Memory Management](https://mlsanity.com/paper/2604.03679/) (2026)
- [HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression](https://mlsanity.com/paper/2606.28831/) (2026)
- [CCF: A Context Compression Framework for Efficient Long-Sequence Language Modeling](https://mlsanity.com/paper/2509.09199/) (2025)
- [S3-Attention:Attention-Aligned Endogenous Retrieval for Memory-Bounded Long-Context Inference](https://mlsanity.com/paper/2601.17702/) (2026)
- [UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference](https://mlsanity.com/paper/2603.18446/) (2026)
- [Adaptive Mass-Segmented KV Compression for Long-Context Reasoning](https://mlsanity.com/paper/2605.23200/) (2026)
- [Moment-KV: Momentum-Based Decode-Time KV Cache Compression for Long Generation](https://mlsanity.com/paper/2605.29873/) (2026)
- [ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs](https://mlsanity.com/paper/2606.00543/) (2026)
- [Parser Transitions Already Reveal Structural Responsibility: KV Persistence for Structured Generation](https://mlsanity.com/paper/2608.28276/) (2026)
- [StepKV: Step-Aware KV Cache Compression for LLM Agents](https://mlsanity.com/paper/2609.22158/) (2026)
- [CORE: COverage CAlibration and Evicted-Mass REdistribution for KV Cache](https://mlsanity.com/paper/2610.02235/) (2026)
- [WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds](https://mlsanity.com/paper/2610.02713/) (2026)

## Abstract (arXiv)

Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation. Despite the numerous efforts in this area, the optimization for the decoding phase is generally ignored. However, we believe such optimization is crucial, especially for long-output generation tasks based on the following two observations: (i) Excessive compression during the prefill phase, which requires specific full context impairs the comprehension of the reasoning task; (ii) Deviation of heavy hitters occurs in the reasoning tasks with long outputs. Therefore, SCOPE, a simple yet efficient framework that separately performs KV cache optimization during the prefill and decoding phases, is introduced. Specifically, the KV cache during the prefill phase is preserved to maintain the essential information, while a novel strategy based on sliding is proposed to select essential heavy hitters for the decoding phase. Memory usage and memory transfer are further optimized using adaptive and discontinuous strategies. Extensive experiments on LongGenBench show the effectiveness and generalization of SCOPE and its compatibility as a plug-in to other prefill-only KV compression methods.