# SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing

arXiv: https://arxiv.org/abs/2512.10411 · HTML: https://mlsanity.com/paper/2512.10411/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [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)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [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)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (2024)
- [LongAlign: A Recipe for Long Context Alignment of Large Language Models](https://mlsanity.com/paper/2401.18058/) (2024)
- [Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning](https://mlsanity.com/paper/2402.13669/) (2024)
- [Sliding Window Attention Training for Efficient Large Language Models](https://mlsanity.com/paper/2502.18845/) (2025)
- [Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models](https://mlsanity.com/paper/2511.18890/) (2025)
- [LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation](https://mlsanity.com/paper/2410.13846/) (2024)
- [RATTENTION: Towards the Minimal Sliding Window Size in Local-Global Attention Models](https://mlsanity.com/paper/2506.15545/) (2025)

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

- [Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation](https://mlsanity.com/paper/2604.10098/) (2026)
- [Prefix Sliding for efficient test-time scaling](https://mlsanity.com/paper/2608.26070/) (2026)
- [Sliding-window beats linear attention](https://mlsanity.com/paper/2608.28444/) (2026)
- [NLL-Guided Full-Attention Layer Selection for Training-Free Sliding-Window Adaptation](https://mlsanity.com/paper/2606.27791/) (2026)

## Abstract (arXiv)

The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity alternative, it suffers from catastrophic long context performance collapse, which stems from two fundamental factors: the training inference mismatch when naively applying SWA to models pretrained with Full Attention (FA), and the inherent structural inability to access distant information when applying SWA to every module at all times. To address these dual challenges, we propose Sliding Window Attention Adaptation (SWAA), a plug and play toolkit of recipes that adapts FA models to SWA without costly pretraining. SWAA systematically combines four core strategies to tackle these distinct issues: (1) Full Attention (FA) Decode and (2) Interleaving FA and SWA layers, which mitigate structural defects by selectively allowing access to distant information; alongside (3) preserving ``sink'' tokens and (4) lightweight fine tuning, which mitigate the training inference mismatch. Our experiments reveal that while isolated strategies are insufficient, specific synergistic combinations effectively recover long context performance. Despite varying computational overheads, our performance efficiency trade off analysis identifies optimal SWAA configurations for diverse scenarios, achieving 30% to 100% speedups for long context inference with acceptable quality retention. Our code, data and model weights are available at https://github.com/yuyijiong/sliding-window-attention-adaptation