# IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

arXiv: https://arxiv.org/abs/2603.12201 · HTML: https://mlsanity.com/paper/2603.12201/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 49 of its 55 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [Jamba: A Hybrid Transformer-Mamba Language Model](https://mlsanity.com/paper/2403.19887/) (2024)
- [MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention](https://mlsanity.com/paper/2407.02490/) (2024)
- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (2024)
- [DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads](https://mlsanity.com/paper/2410.10819/) (2024)
- [MoBA: Mixture of Block Attention for Long-Context LLMs](https://mlsanity.com/paper/2502.13189/) (2025)
- [Kimi Linear: An Expressive, Efficient Attention Architecture](https://mlsanity.com/paper/2510.26692/) (2025)
- [Generalizing Verifiable Instruction Following](https://mlsanity.com/paper/2507.02833/) (2025)
- [MiMo-V2-Flash Technical Report](https://mlsanity.com/paper/2601.02780/) (2026)
- [MiniMax-01: Scaling Foundation Models with Lightning Attention](https://mlsanity.com/paper/2501.08313/) (2025)
- [You Only Cache Once: Decoder-Decoder Architectures for Language Models](https://mlsanity.com/paper/2405.05254/) (2024)
- [XAttention: Block Sparse Attention with Antidiagonal Scoring](https://mlsanity.com/paper/2503.16428/) (2025)
- [Reducing Transformer Key-Value Cache Size with Cross-Layer Attention](https://mlsanity.com/paper/2405.12981/) (2024)
- [MiniCache: KV Cache Compression in Depth Dimension for Large Language Models](https://mlsanity.com/paper/2405.14366/) (2024)
- [SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs](https://mlsanity.com/paper/2410.13276/) (2024)

## Built on by (most cited first, 30 of 31)

- [On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability](https://mlsanity.com/paper/2608.30320/) (2026)
- [HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention](https://mlsanity.com/paper/2603.28458/) (2026)
- [MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference](https://mlsanity.com/paper/2605.07363/) (2026)
- [IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference](https://mlsanity.com/paper/2605.25475/) (2026)
- [When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression](https://mlsanity.com/paper/2605.08234/) (2026)
- [SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2606.04511/) (2026)
- [DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention](https://mlsanity.com/paper/2605.18753/) (2026)
- [LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget](https://mlsanity.com/paper/2607.14952/) (2026)
- [PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention](https://mlsanity.com/paper/2607.24593/) (2026)
- [HiSparse: Scaling Sparse-Attention Decoding with Hierarchical KV Cache Management](https://mlsanity.com/paper/2608.07009/) (2026)
- [You Only Index Once: Cross-Layer Sparse Attention with Shared Routing](https://mlsanity.com/paper/2606.06467/) (2026)
- [LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention](https://mlsanity.com/paper/2607.11976/) (2026)
- [LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing](https://mlsanity.com/paper/2608.01662/) (2026)
- [Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics](https://mlsanity.com/paper/2606.01502/) (2026)
- [Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents](https://mlsanity.com/paper/2606.06453/) (2026)
- [Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry](https://mlsanity.com/paper/2608.06849/) (2026)
- [Trace as State: Reasoning Traces as Conditional States for Long-Context Transformers](https://mlsanity.com/paper/2609.02702/) (2026)
- [Heterogeneous LLM Serving with General-Purpose Processing-Near-Memory for Retrieval-Based Sparse Attention](https://mlsanity.com/paper/2608.03555/) (2026)
- [Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning](https://mlsanity.com/paper/2608.16620/) (2026)
- [Learning how to Forget: Fine-tuning for Long-Context Sparse Attention](https://mlsanity.com/paper/2608.19920/) (2026)
- [Block-Sparse Attention with Semantic-Geometric Decoupled Routing](https://mlsanity.com/paper/2609.22884/) (2026)
- [Block Sparse Attention with Log-Linear Complexity](https://mlsanity.com/paper/2609.31093/) (2026)
- [SparseEngine: Sparse-First Inference Engine](https://mlsanity.com/paper/2609.39068/) (2026)
- [Characterizing High Bandwidth Flash for LLM Serving](https://mlsanity.com/paper/2609.39131/) (2026)
- [The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends](https://mlsanity.com/paper/2609.39661/) (2026)
- [VASC: Value-Aware Sparse Attention with Cross-Layer Memory for Efficient 3D Reconstruction](https://mlsanity.com/paper/2610.01013/) (2026)
- [LatentIndex: Cross-Layer Sharing with Layer-Specific Selection for Sparse Attention](https://mlsanity.com/paper/2610.04635/) (2026)
- [SPIN: Shadow Predictive Indexer for Sparse Attention](https://mlsanity.com/paper/2610.09025/) (2026)
- [Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position](https://mlsanity.com/paper/2610.10114/) (2026)
- [Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy](https://mlsanity.com/paper/2610.13708/) (2026)

## Abstract (arXiv)

Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and DeepSeek Sparse Attention (DSA) is a representative production-grade solution: a lightweight lightning indexer selects the top-k most relevant tokens per query, reducing core attention from O(L2) to O(Lk). However, the indexer itself retains O(L2) complexity and must run independently at every layer, despite the fact that the resulting top-k selections are highly similar across consecutive layers. We present IndexCache, which exploits this cross-layer redundancy by partitioning layers into a small set of Full layers that run their own indexers and a majority of Shared layers that simply reuse the nearest Full layer's top-k indices. We propose two complementary approaches to determine and optimize this configuration. Training-free IndexCache applies a greedy search algorithm that selects which layers to retain indexers by directly minimizing language modeling loss on a calibration set, requiring no weight updates. Training-aware IndexCache introduces a multi-layer distillation loss that trains each retained indexer against the averaged attention distributions of all layers it serves, enabling even simple interleaved patterns to match full-indexer accuracy. Experimental results on a 30B DSA model show that IndexCache can remove 75% of indexer computations with negligible quality degradation, achieving up to 1.82× prefill speedup and 1.48× decode speedup compared to standard DSA. These positive results are further confirmed by our preliminary experiments on the production-scale GLM-5 model (Figure 1).