# InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU

arXiv: https://arxiv.org/abs/2502.08910 · HTML: https://mlsanity.com/paper/2502.08910/

## Key facts

- Cited by 7 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 19 of its 27 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention](https://mlsanity.com/paper/2407.02490/) (2024)
- [InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://mlsanity.com/paper/2402.04617/) (2024)
- [LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning](https://mlsanity.com/paper/2401.01325/) (2024)
- [LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models](https://mlsanity.com/paper/2308.16137/) (2023)
- [LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference](https://mlsanity.com/paper/2407.14057/) (2024)
- [EXAONE 3.5: Series of Large Language Models for Real-world Use Cases](https://mlsanity.com/paper/2412.04862/) (2024)
- [EXAONE 3.0 7.8B Instruction Tuned Language Model](https://mlsanity.com/paper/2408.03541/) (2024)
- [A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention](https://mlsanity.com/paper/2406.09827/) (2024)
- [SEA: Sparse Linear Attention with Estimated Attention Mask](https://mlsanity.com/paper/2310.01777/) (2023)

## Built on by (most cited first, 7 of 7)

- [Training-Free Efficient Video Generation via Dynamic Token Carving](https://mlsanity.com/paper/2505.16864/) (2025)
- [FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression](https://mlsanity.com/paper/2507.20030/) (2025)
- [Memory in Large Language Models: Mechanisms, Evaluation and Evolution](https://mlsanity.com/paper/2509.18868/) (2025)
- [SQuat: Subspace-orthogonal KV Cache Quantization](https://mlsanity.com/paper/2503.24358/) (2025)
- [Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction](https://mlsanity.com/paper/2505.11254/) (2025)
- [PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents](https://mlsanity.com/paper/2605.19932/) (2026)
- [Squeezing the Cache, Preserving the Truth: Monotonic Equipotential Allocation with Geodesia-KV](https://mlsanity.com/paper/2608.23599/) (2026)

## Abstract (arXiv)

In modern large language models (LLMs), handling very long context lengths presents significant challenges as it causes slower inference speeds and increased memory costs. Additionally, most existing pre-trained LLMs fail to generalize beyond their original training sequence lengths. To enable efficient and practical long-context utilization, we introduce InfiniteHiP, a novel, and practical LLM inference framework that accelerates processing by dynamically eliminating irrelevant context tokens through a modular hierarchical token pruning algorithm. Our method also allows generalization to longer sequences by selectively applying various RoPE adjustment methods according to the internal attention patterns within LLMs. Furthermore, we offload the key-value cache to host memory during inference, significantly reducing GPU memory pressure. As a result, InfiniteHiP enables the processing of up to 3 million tokens on a single L40s 48GB GPU -- 3x larger -- without any permanent loss of context information. Our framework achieves an 18.95x speedup in attention decoding for a 1 million token context without requiring additional training. We implement our method in the SGLang framework and demonstrate its effectiveness and practicality through extensive evaluations.