# Layer-Condensed KV Cache for Efficient Inference of Large Language Models

arXiv: https://arxiv.org/abs/2405.10637 · HTML: https://mlsanity.com/paper/2405.10637/

## Key facts

- Cited by 59 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 25 of its 38 references that are in the map.
- First posted on arXiv 17 May 2024.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [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)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [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)
- [Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time](https://mlsanity.com/paper/2305.17118/) (2023)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference](https://mlsanity.com/paper/2403.09054/) (2024)
- [The MiniPile Challenge for Data-Efficient Language Models](https://mlsanity.com/paper/2304.08442/) (2023)
- [Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers](https://mlsanity.com/paper/2101.00234/) (2021)
- [Context Compression for Auto-regressive Transformers with Sentinel Tokens](https://mlsanity.com/paper/2310.08152/) (2023)
- [Probabilistic Transformer: A Probabilistic Dependency Model for Contextual Word Representation](https://mlsanity.com/paper/2311.15211/) (2023)

## Built on by (most cited first, 30 of 59)

- [When Attention Sink Emerges in Language Models: An Empirical View](https://mlsanity.com/paper/2410.10781/) (2024)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation](https://mlsanity.com/paper/2507.10524/) (2025)
- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [MiniCache: KV Cache Compression in Depth Dimension for Large Language Models](https://mlsanity.com/paper/2405.14366/) (2024)
- [ThinK: Thinner Key Cache by Query-Driven Pruning](https://mlsanity.com/paper/2407.21018/) (2024)
- [Cache-to-Cache: Direct Semantic Communication Between Large Language Models](https://mlsanity.com/paper/2510.03215/) (2025)
- [ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2502.00299/) (2025)
- [KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing](https://mlsanity.com/paper/2410.18517/) (2024)
- [Block Transformer: Global-to-Local Language Modeling for Fast Inference](https://mlsanity.com/paper/2406.02657/) (2024)
- [The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks](https://mlsanity.com/paper/2603.05498/) (2026)
- [Parallel Continuous Chain-of-Thought with Jacobi Iteration](https://mlsanity.com/paper/2506.18582/) (2025)
- [Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2601.06007/) (2026)
- [A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference](https://mlsanity.com/paper/2410.14442/) (2024)
- [A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression](https://mlsanity.com/paper/2412.17483/) (2024)
- [Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression](https://mlsanity.com/paper/2502.01941/) (2025)
- [xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction](https://mlsanity.com/paper/2503.18893/) (2025)
- [PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space](https://mlsanity.com/paper/2509.23184/) (2025)
- [Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse](https://mlsanity.com/paper/2608.03893/) (2026)
- [KV Prediction for Improved Time to First Token](https://mlsanity.com/paper/2410.08391/) (2024)
- [BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference](https://mlsanity.com/paper/2410.23079/) (2024)
- [SQuat: Subspace-orthogonal KV Cache Quantization](https://mlsanity.com/paper/2503.24358/) (2025)
- [Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models](https://mlsanity.com/paper/2505.12343/) (2025)
- [Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers](https://mlsanity.com/paper/2512.03870/) (2025)
- [Cross-layer Attention Sharing for Pre-trained Large Language Models](https://mlsanity.com/paper/2408.01890/) (2024)
- [Mixed-Precision Quantization for Language Models: Techniques and Prospects](https://mlsanity.com/paper/2510.16805/) (2025)
- [Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems](https://mlsanity.com/paper/2511.22880/) (2025)
- [Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse](https://mlsanity.com/paper/2602.01203/) (2026)
- [Inference-Friendly Models With MixAttention](https://mlsanity.com/paper/2409.15012/) (2024)
- [NOSA: Native and Offloadable Sparse Attention](https://mlsanity.com/paper/2510.13602/) (2025)

## Abstract (arXiv)

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the transformer architecture consumes a significant amount of memory, especially when the number of layers is large for deep language models. In this paper, we propose a novel method that only computes and caches the KVs of a small number of layers, thus significantly saving memory consumption and improving inference throughput. Our experiments on large language models show that our method achieves up to 26× higher throughput than standard transformers and competitive performance in language modeling and downstream tasks. In addition, our method is orthogonal to existing transformer memory-saving techniques, so it is straightforward to integrate them with our model, achieving further improvement in inference efficiency. Our code is available at https://github.com/whyNLP/LCKV.