# HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving

arXiv: https://arxiv.org/abs/2504.10724 · HTML: https://mlsanity.com/paper/2504.10724/

## Key facts

- Cited by 8 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 79 of its 114 references that are in the map.
- First posted on arXiv 14 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, 30 of 79)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (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)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)

## Built on by (most cited first, 8 of 8)

- [AI Flow: Perspectives, Scenarios, and Approaches](https://mlsanity.com/paper/2506.12479/) (2025)
- [Dynamic Rebatching for Efficient Early-Exit Inference with DREX](https://mlsanity.com/paper/2512.15705/) (2025)
- [Ruyi2 Technical Report](https://mlsanity.com/paper/2602.22543/) (2026)
- [The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces](https://mlsanity.com/paper/2605.27965/) (2026)
- [SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning](https://mlsanity.com/paper/2603.23483/) (2026)
- [LLM-CoOpt: A Co-Design and Optimization Framework for Efficient LLM Inference on Heterogeneous Platforms](https://mlsanity.com/paper/2602.09323/) (2026)
- [Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit](https://mlsanity.com/paper/2609.12337/) (2026)
- [SpecQuant: Speculative Decoding with Multi-Parent Quantization for Adaptive LLM Inference](https://mlsanity.com/paper/2609.21704/) (2026)

## Abstract (arXiv)

Early-Exit Large Language Models (EE-LLMs) enable high throughput inference by allowing tokens to exit early at intermediate layers. However, their throughput is limited by the computational and memory savings. Existing EE-LLM frameworks rely on a single model and therefore, their token generation latencies are bottlenecked by tokens that do not exit early and traverse additional layers. Moreover, early exits are only known at runtime and depend on the request. Therefore, these frameworks load the weights of all model layers even though large portions remain unused when tokens exit early. The lack of memory savings limit us from scaling the batch sizes. We propose textitHELIOS, a framework that improves both token generation latency and batch sizes to enable high-throughput in EE-LLMs. HELIOS exploits two insights. textitFirst, early exits are often complimentary across models, tokens that do not exit early on one model often take an early-exit on another. HELIOS employs multiple models and dynamically switches between them to collectively maximize the number of tokens that exit early, and minimize token generation latencies. textitSecond, even when a predicted token does not exit early due to poor confidence, it often remains unchanged even after additional layer traversal. HELIOS greedily allows such tokens to exit early and only loads the weights of the most likely to be used layers, yielding memory savings which is then re-purposed to increase batch sizes. HELIOS employs real-time profiling to accurately identify the early-exit distributions, and adaptively switches between models by tracking tokens in real-time to minimize the performance degradation caused by greedy model loading and exiting. Our evaluations show that HELIOS achieves 1.48× higher throughput and 15.14× larger batch size compared to existing EE-LLM frameworks.