# DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration

arXiv: https://arxiv.org/abs/2506.11104 · HTML: https://mlsanity.com/paper/2506.11104/

## Key facts

- Cited by 4 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 32 of its 38 references that are in the map.
- First posted on arXiv 6 Jun 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 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [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)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [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)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Efficient Content-Based Sparse Attention with Routing Transformers](https://mlsanity.com/paper/2003.05997/) (2020)
- [Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time](https://mlsanity.com/paper/2305.17118/) (2023)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [Axial Attention in Multidimensional Transformers](https://mlsanity.com/paper/1912.12180/) (2019)
- [Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention](https://mlsanity.com/paper/2403.19708/) (2024)
- [Adaptively Sparse Transformers](https://mlsanity.com/paper/1909.00015/) (2019)
- [Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference](https://mlsanity.com/paper/2403.09054/) (2024)
- [LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization](https://mlsanity.com/paper/2301.13298/) (2023)
- [O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers](https://mlsanity.com/paper/2006.04862/) (2020)
- [ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition](https://mlsanity.com/paper/2402.15220/) (2024)
- [LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K](https://mlsanity.com/paper/2402.05136/) (2024)
- [MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool](https://mlsanity.com/paper/2406.17565/) (2024)
- [Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers](https://mlsanity.com/paper/2006.03555/) (2020)
- [Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions](https://mlsanity.com/paper/2112.05561/) (2021)
- [ETC: Encoding Long and Structured Inputs in Transformers](https://mlsanity.com/paper/2004.08483/) (2020)
- [BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching](https://mlsanity.com/paper/2412.03594/) (2024)
- [Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks](https://mlsanity.com/paper/1906.04393/) (2019)
- [DiffKV: Differentiated Memory Management for Large Language Models with Parallel KV Compaction](https://mlsanity.com/paper/2412.03131/) (2024)
- [LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management](https://mlsanity.com/paper/2410.00428/) (2024)
- [BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference](https://mlsanity.com/paper/2410.23079/) (2024)

## Built on by (most cited first, 4 of 4)

- [VideoNSA: Native Sparse Attention Scales Video Understanding](https://mlsanity.com/paper/2510.02295/) (2025)
- [Trainable Dynamic Mask Sparse Attention](https://mlsanity.com/paper/2508.02124/) (2025)
- [Hasse Diagrams for Attention: A Partial Order Framework for Designing Transformer Masks](https://mlsanity.com/paper/2606.09951/) (2026)
- [CoWindow Attention: Full Causal Coverage Is a Collective Property](https://mlsanity.com/paper/2609.32704/) (2026)

## Abstract (arXiv)

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined masks, failing to capture heterogeneous attention patterns. This results in suboptimal token interactions, limiting adaptability and retrieval accuracy in long-sequence tasks. This work introduces a dynamic sparse attention mechanism that assigns adaptive masks at the attention-map level, preserving heterogeneous patterns across layers and heads. Unlike existing approaches, our method eliminates the need for fine-tuning and predefined mask structures while maintaining computational efficiency. By learning context-aware attention structures, it achieves high alignment with full-attention models, ensuring minimal performance degradation while reducing memory and compute overhead. This approach provides a scalable alternative to full attention, enabling the practical deployment of large-scale Large Language Models (LLMs) without sacrificing retrieval performance. DAM is available at: https://github.com/HanzhiZhang-Ulrica/DAM.