# IAM: Efficient Inference through Attention Mapping between Different-scale LLMs

arXiv: https://arxiv.org/abs/2507.11953 · HTML: https://mlsanity.com/paper/2507.11953/

## Key facts

- Cited by 10 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 20 of its 27 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [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)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [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)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (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)
- [Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time](https://mlsanity.com/paper/2305.17118/) (2023)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation](https://mlsanity.com/paper/2203.16487/) (2022)
- [PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference](https://mlsanity.com/paper/2405.12532/) (2024)
- [You Only Cache Once: Decoder-Decoder Architectures for Language Models](https://mlsanity.com/paper/2405.05254/) (2024)
- [Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks](https://mlsanity.com/paper/2407.08454/) (2024)

## Built on by (most cited first, 10 of 10)

- [Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse](https://mlsanity.com/paper/2608.03893/) (2026)
- [CacheBridge: Efficient Cross-Model KV Cache Transfer](https://mlsanity.com/paper/2609.00891/) (2026)
- [CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models](https://mlsanity.com/paper/2508.17243/) (2025)
- [A Layered Intuition -- Method Model with Scope Extension for LLM Reasoning](https://mlsanity.com/paper/2510.10592/) (2025)
- [From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons](https://mlsanity.com/paper/2605.27387/) (2026)
- [From Parameters to Performance: A Data-Driven Study on LLM Structure and Development](https://mlsanity.com/paper/2509.18136/) (2025)
- [ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2605.16360/) (2026)
- [Emergent Structure in the Marginal Attention Space of Language Models](https://mlsanity.com/paper/2610.03109/) (2026)
- [Accelerating Cross-Model LLM Inference via Attention Map Reuse](https://mlsanity.com/paper/2610.14688/) (2026)
- [CacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff](https://mlsanity.com/paper/2610.15509/) (2026)

## Abstract (arXiv)

LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the models, without leveraging external information for optimization. We identify the high similarity of attention matrices across different-scale LLMs, which offers a novel perspective for optimization. We first conduct a comprehensive analysis of how to measure similarity, how to select mapping Layers and whether mapping is consistency. Based on these insights, we introduce the IAM framework, which achieves dual benefits of accelerated attention computation and reduced KV cache usage by performing attention mapping between small and large LLMs. Our experimental results demonstrate that IAM can accelerate prefill by 15% and reduce KV cache usage by 22.1% without appreciably sacrificing performance. Experiments on different series of models show the generalizability of IAM. Importantly, it is also orthogonal to many existing KV cache optimization methods, making it a versatile addition to the current toolkit for enhancing LLM efficiency.