# River-LLM: Large Language Model Seamless Exit Based on KV Share

arXiv: https://arxiv.org/abs/2604.18396 · HTML: https://mlsanity.com/paper/2604.18396/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Placed in

- Efficient LLM inference and serving / [Early exit and edge inference](https://mlsanity.com/inference/early-exit-and-edge-inference/)

## Builds on (most cited first, 26 of 26)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding](https://mlsanity.com/paper/2404.16710/) (2024)
- [Depth-Adaptive Transformer](https://mlsanity.com/paper/1910.10073/) (2019)
- [Dynamic Early Exit in Reasoning Models](https://mlsanity.com/paper/2504.15895/) (2025)
- [Not All Layers of LLMs Are Necessary During Inference](https://mlsanity.com/paper/2403.02181/) (2024)
- [SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference](https://mlsanity.com/paper/2307.02628/) (2023)
- [EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism](https://mlsanity.com/paper/2312.04916/) (2023)
- [Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition](https://mlsanity.com/paper/1509.08971/) (2015)
- [Mixture of Nested Experts: Adaptive Processing of Visual Tokens](https://mlsanity.com/paper/2407.19985/) (2024)
- [Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inference](https://mlsanity.com/paper/2206.04685/) (2022)
- [SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting](https://mlsanity.com/paper/2504.08850/) (2025)
- [Progressive Mixed-Precision Decoding for Efficient LLM Inference](https://mlsanity.com/paper/2410.13461/) (2024)
- [AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference](https://mlsanity.com/paper/2501.02336/) (2025)
- [RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient Inference](https://mlsanity.com/paper/2405.15198/) (2024)
- [InfoQ: Mixed-Precision Quantization via Global Information Flow](https://mlsanity.com/paper/2508.04753/) (2025)
- [DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment](https://mlsanity.com/paper/2508.06041/) (2025)

## Built on by (most cited first, 1 of 1)

- [Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching](https://mlsanity.com/paper/2608.09444/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated exceptional performance across diverse domains but are increasingly constrained by high inference latency. Early Exit has emerged as a promising solution to accelerate inference by dynamically bypassing redundant layers. However, in decoder-only architectures, the efficiency of Early Exit is severely bottlenecked by the KV Cache Absence problem, where skipped layers fail to provide the necessary historical states for subsequent tokens. Existing solutions, such as recomputation or masking, either introduce significant latency overhead or incur severe precision loss, failing to bridge the gap between theoretical layer reduction and practical wall-clock speedup. In this paper, we propose River-LLM, a training-free framework that enables seamless token-level Early Exit. River-LLM introduces a lightweight KV-Shared Exit River that allows the backbone's missing KV cache to be naturally generated and preserved during the exit process, eliminating the need for costly recovery operations. Furthermore, we utilize state transition similarity within decoder blocks to predict cumulative KV errors and guide precise exit decisions. Extensive experiments on mathematical reasoning and code generation tasks demonstrate that River-LLM achieves 1.53 to 2.16 times of practical speedup while maintaining high generation quality.