# Star Attention: Efficient LLM Inference over Long Sequences

arXiv: https://arxiv.org/abs/2411.17116 · HTML: https://mlsanity.com/paper/2411.17116/

## Key facts

- Cited by 25 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 28 of its 41 references that are in the map.
- First posted on arXiv 26 Nov 2024.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [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)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (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)
- [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024)
- [Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention](https://mlsanity.com/paper/2404.07143/) (2024)
- [InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://mlsanity.com/paper/2402.04617/) (2024)
- [Online normalizer calculation for softmax](https://mlsanity.com/paper/1805.02867/) (2018)
- [You Only Cache Once: Decoder-Decoder Architectures for Language Models](https://mlsanity.com/paper/2405.05254/) (2024)
- [Sequence Parallelism: Long Sequence Training from System Perspective](https://mlsanity.com/paper/2105.13120/) (2021)
- [LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models](https://mlsanity.com/paper/2308.16137/) (2023)
- [Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models](https://mlsanity.com/paper/2401.04658/) (2024)
- [ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching](https://mlsanity.com/paper/2403.17312/) (2024)
- [Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters](https://mlsanity.com/paper/2408.04093/) (2024)
- [E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning](https://mlsanity.com/paper/2409.06679/) (2024)
- [Writing in the Margins: Better Inference Pattern for Long Context Retrieval](https://mlsanity.com/paper/2408.14906/) (2024)

## Built on by (most cited first, 25 of 25)

- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Training-free and Adaptive Sparse Attention for Efficient Long Video Generation](https://mlsanity.com/paper/2502.21079/) (2025)
- [SCBench: A KV Cache-Centric Analysis of Long-Context Methods](https://mlsanity.com/paper/2412.10319/) (2024)
- [MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention](https://mlsanity.com/paper/2504.16083/) (2025)
- [ParallelComp: Parallel Long-Context Compressor for Length Extrapolation](https://mlsanity.com/paper/2502.14317/) (2025)
- [Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention](https://mlsanity.com/paper/2503.08640/) (2025)
- [FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models](https://mlsanity.com/paper/2508.01506/) (2025)
- [Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data](https://mlsanity.com/paper/2505.02130/) (2025)
- [Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning](https://mlsanity.com/paper/2509.06461/) (2025)
- [Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction](https://mlsanity.com/paper/2505.11254/) (2025)
- [FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel](https://mlsanity.com/paper/2508.18224/) (2025)
- [Attention Is Not All You Need: The Importance of Feedforward Networks in Transformer Models](https://mlsanity.com/paper/2505.06633/) (2025)
- [CTR-Sink: Attention Sink for Language Models in Click-Through Rate Prediction](https://mlsanity.com/paper/2508.03668/) (2025)
- [APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs](https://mlsanity.com/paper/2502.12085/) (2025)
- [Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems](https://mlsanity.com/paper/2502.14305/) (2025)
- [LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding](https://mlsanity.com/paper/2606.04302/) (2026)
- [More Than a Quick Glance: Overcoming the Greedy Bias in KV-Cache Compression](https://mlsanity.com/paper/2602.02199/) (2026)
- [Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision](https://mlsanity.com/paper/2603.13306/) (2026)
- [AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse](https://mlsanity.com/paper/2605.03644/) (2026)
- [Overlapping Schwarz Attention: Hierarchical Attention via Domain Decomposition](https://mlsanity.com/paper/2606.18525/) (2026)
- [APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention](https://mlsanity.com/paper/2601.21444/) (2026)
- [Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores](https://mlsanity.com/paper/2605.12491/) (2026)
- [Dropping the Anchor: Statistical Context Summarization for Distributed Systems via Pulsar Attention](https://mlsanity.com/paper/2607.20457/) (2026)
- [No More Free Lunch: Corpus Task Complexity Matters as Corpora Grow](https://mlsanity.com/paper/2609.29245/) (2026)
- [HHR: Hierarchical Hash Retrieval for Efficient LLM Generation](https://mlsanity.com/paper/2610.01230/) (2026)

## Abstract (arXiv)

Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism. We introduce Star Attention, a two-phase block-sparse approximation that improves computational efficiency by sharding attention across multiple hosts while minimizing communication overhead. In the first phase, the context is processed using blockwise-local attention across hosts, in parallel. In the second phase, query and response tokens attend to all prior cached tokens through sequence-global attention. Star Attention integrates seamlessly with most Transformer-based LLMs trained with global attention, reducing memory requirements and inference time by up to 11x while preserving 97-100% of accuracy.