# In-context KV-Cache Eviction for LLMs via Attention-Gate

arXiv: https://arxiv.org/abs/2410.12876 · HTML: https://mlsanity.com/paper/2410.12876/

## Key facts

- Cited by 13 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 27 of its 36 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [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)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [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)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [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)
- [SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning](https://mlsanity.com/paper/2012.09852/) (2020)
- [Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets](https://mlsanity.com/paper/1903.05662/) (2019)
- [Transformers are Multi-State RNNs](https://mlsanity.com/paper/2401.06104/) (2024)
- [Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers](https://mlsanity.com/paper/2305.15805/) (2023)
- [NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time](https://mlsanity.com/paper/2408.03675/) (2024)
- [A2SF: Accumulative Attention Scoring with Forgetting Factor for Token Pruning in Transformer Decoder](https://mlsanity.com/paper/2407.20485/) (2024)

## Built on by (most cited first, 13 of 13)

- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [SeerAttention-R: Sparse Attention Adaptation for Long Reasoning](https://mlsanity.com/paper/2506.08889/) (2025)
- [Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs](https://mlsanity.com/paper/2512.03324/) (2025)
- [AttentionPredictor: Temporal Patterns Matter for KV Cache Compression](https://mlsanity.com/paper/2502.04077/) (2025)
- [SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference](https://mlsanity.com/paper/2508.02751/) (2025)
- [From Masks to Worlds: A Hitchhiker's Guide to World Models](https://mlsanity.com/paper/2510.20668/) (2025)
- [KV Admission: Learning What to Write for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2512.17452/) (2025)
- [Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction](https://mlsanity.com/paper/2510.20787/) (2025)
- [TABES: Trajectory-Aware Backward-on-Entropy Steering for Masked Diffusion Models](https://mlsanity.com/paper/2602.00250/) (2026)
- [Language Models Can Control Their Own Attention](https://mlsanity.com/paper/2609.02737/) (2026)
- [ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction](https://mlsanity.com/paper/2609.36835/) (2026)
- [Sigmoid Attention as a Better Substrate for Learned KV Cache Eviction](https://mlsanity.com/paper/2608.23296/) (2026)
- [PAGE: Partition-Aware Gated KV-Cache Eviction](https://mlsanity.com/paper/2609.22157/) (2026)

## Abstract (arXiv)

The KV-Cache technique has become the standard for the inference of large language models (LLMs). Yet, it is widely criticized that KV-Cache can become a bottleneck of the LLM inference system. This paper enables a novel dynamic KV-Cache eviction policy by injecting a lightweight module called Attention-Gate to the model. It accepts the global context as input and yields eviction flags for each token. The self-attention modules in the model proceed according to the flags and cache only a subset of the KV states for next token prediction. The Attention-Gates can yield various flags for different heads and layers and be easily tuned on top of a pre-trained LLM via continual pre-training or supervised fine-tuning. The computational and memory overhead introduced by Attention-Gates can be minimal. We empirically evaluate the proposed approach across multiple scenarios, showing that effective eviction of redundant tokens can not only improve efficiency but also enhance performance.