# One Jump Is All You Need: Short-Cutting Transformers for Early Exit Prediction with One Jump to Fit All Exit Levels

arXiv: https://arxiv.org/abs/2504.13984 · HTML: https://mlsanity.com/paper/2504.13984/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 9 of its 10 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## 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, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [The Right Tool for the Job: Matching Model and Instance Complexities](https://mlsanity.com/paper/2004.07453/) (2020)
- [Jump to Conclusions: Short-Cutting Transformers With Linear Transformations](https://mlsanity.com/paper/2303.09435/) (2023)
- [Normalized Narrow Jump To Conclusions: Normalized Narrow Shortcuts for Parameter Efficient Early Exit Transformer Prediction](https://mlsanity.com/paper/2409.14091/) (2024)

## Abstract (arXiv)

To reduce the time and computational costs of inference of large language models, there has been interest in parameter-efficient low-rank early-exit casting of transformer hidden-representations to final-representations. Such low-rank short-cutting has been shown to outperform identity shortcuts at early model stages while offering parameter-efficiency in shortcut jumps. However, current low-rank methods maintain a separate early-exit shortcut jump to final-representations for each transformer intermediate block-level during inference. In this work, we propose selection of a single One-Jump-Fits-All (OJFA) low-rank shortcut that offers over a 30x reduction in shortcut parameter costs during inference. We show that despite this extreme reduction, our OJFA choice largely matches the performance of maintaining multiple shortcut jumps during inference and offers stable precision from all transformer block-levels for GPT2-XL, Phi3-Mini and Llama2-7B transformer models.