# From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs

arXiv: https://arxiv.org/abs/2606.09508 · HTML: https://mlsanity.com/paper/2606.09508/

## Key facts

- Cited by 1 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 24 of its 29 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [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)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention](https://mlsanity.com/paper/2407.02490/) (2024)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads](https://mlsanity.com/paper/2410.10819/) (2024)
- [Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference](https://mlsanity.com/paper/2407.11550/) (2024)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference](https://mlsanity.com/paper/2405.12532/) (2024)
- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference](https://mlsanity.com/paper/2502.20766/) (2025)
- [RazorAttention: Efficient KV Cache Compression Through Retrieval Heads](https://mlsanity.com/paper/2407.15891/) (2024)
- [NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities](https://mlsanity.com/paper/2407.11963/) (2024)
- [UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective](https://mlsanity.com/paper/2410.03090/) (2024)
- [CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs](https://mlsanity.com/paper/2409.12490/) (2024)
- [KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference](https://mlsanity.com/paper/2511.11907/) (2025)
- [LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences](https://mlsanity.com/paper/2510.11292/) (2025)
- [SABlock: Semantic-Aware KV Cache Eviction with Adaptive Compression Block Size](https://mlsanity.com/paper/2510.22556/) (2025)

## Built on by (most cited first, 1 of 1)

- [PAGE: Partition-Aware Gated KV-Cache Eviction](https://mlsanity.com/paper/2609.22157/) (2026)

## Abstract (arXiv)

Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, overlooking the substantial variation in attention behavior among heads and contexts. We observe two distinct entropy patterns among attention heads: Rigid Heads, whose entropy stays near zero across input segments, and Dynamic Heads, whose entropy fluctuates significantly. Crucially, the distribution of these types is context-dependent and cannot be predetermined offline. We therefore propose EntropyInfer, a training-free framework that uses attention entropy to adaptively allocate compute at the granularity of individual heads and segments during prefilling. For decoding, we introduce a latent KV cache compression scheme that leverages generated output tokens, rather than prefill tokens alone, to identify and retain the most critical cache entries. Extensive experiments on Llama, Qwen and openPangu model series show that EntropyInfer consistently outperforms baselines including SnapKV, AdaKV, and CritiPrefill, achieving up to 2.39× end-to-end speedup beyond 100k tokens with minimal quality degradation compared to full attention. The code is released in https://github.com/SHA-4096/EntropyInfer.