# Dynamic Rebatching for Efficient Early-Exit Inference with DREX

arXiv: https://arxiv.org/abs/2512.15705 · HTML: https://mlsanity.com/paper/2512.15705/

## Key facts

- Cited by 2 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 36 of its 47 references that are in the map.
- First posted on arXiv 17 Dec 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, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [Confident Adaptive Language Modeling](https://mlsanity.com/paper/2207.07061/) (2022)
- [LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding](https://mlsanity.com/paper/2404.16710/) (2024)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [Mixture-of-Depths: Dynamically allocating compute in transformer-based language models](https://mlsanity.com/paper/2404.02258/) (2024)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [Depth-Adaptive Transformer](https://mlsanity.com/paper/1910.10073/) (2019)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation](https://mlsanity.com/paper/2507.10524/) (2025)
- [vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention](https://mlsanity.com/paper/2405.04437/) (2024)
- [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)
- [Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding](https://mlsanity.com/paper/2310.05424/) (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)
- [Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism](https://mlsanity.com/paper/2406.03853/) (2024)
- [Adaptive Layer-skipping in Pre-trained LLMs](https://mlsanity.com/paper/2503.23798/) (2025)
- [SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting](https://mlsanity.com/paper/2504.08850/) (2025)

## Built on by (most cited first, 2 of 2)

- [Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching](https://mlsanity.com/paper/2608.09444/) (2026)
- [vSkipper: Translating Dynamic Layer Skipping into LLM Serving Gains](https://mlsanity.com/paper/2609.37062/) (2026)

## Abstract (arXiv)

Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However, traditional batching frameworks are ill-suited for EE LLMs, as not all requests in a batch may be ready to exit at the same time. Existing solutions either force a uniform decision on the batch, which overlooks EE opportunities, or degrade output quality by forcing premature exits. We propose Dynamic Rebatching, a solution where we dynamically reorganize the batch at each early-exit point. Requests that meet the exit criteria are immediately processed, while those that continue are held in a buffer, re-grouped into a new batch, and forwarded to deeper layers. We introduce DREX, an early-exit inference system that implements Dynamic Rebatching with two key optimizations: 1) a copy-free rebatching buffer that avoids physical data movement, and 2) an EE and SLA-aware scheduler that analytically predicts whether a given rebatching operation will be profitable. DREX also efficiently handles the missing KV cache from skipped layers using memory-efficient state-copying. Our evaluation shows that DREX improves throughput by 2-12% compared to baseline approaches while maintaining output quality. Crucially, DREX completely eliminates involuntary exits, providing a key guarantee for preserving the output quality intended by the EE model.