Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kumar, Avinash, Nag, Shashank, Clemons, Jason, John, Lizy, Das, Poulami
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Test-Time Speculation
by: Kumar, Avinash, et al.
Published: (2026)

HiSpec: Hierarchical Speculative Decoding for LLMs
by: Kumar, Avinash, et al.
Published: (2025)

CEEBERT: Cross-Domain Inference in Early Exit BERT
by: Bajpai, Divya Jyoti, et al.
Published: (2024)

TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference
by: Jaber, Jaber, et al.
Published: (2026)

Accelerating Large Language Model Inference with Self-Supervised Early Exits
by: Valade, Florian
Published: (2024)

LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference
by: Kapadia, Shashank, et al.
Published: (2026)

Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs
by: Ghadia, Ravi, et al.
Published: (2025)

Enhancing Domain-Specific Retrieval-Augmented Generation: Synthetic Data Generation and Evaluation using Reasoning Models
by: Jadon, Aryan, et al.
Published: (2025)

A Survey of Early Exit Deep Neural Networks in NLP
by: Bajpai, Divya Jyoti, et al.
Published: (2025)

BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts
by: Bajpai, Divya Jyoti, et al.
Published: (2025)

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
by: Elhoushi, Mostafa, et al.
Published: (2024)

Universal Model Routing for Efficient LLM Inference
by: Jitkrittum, Wittawat, et al.
Published: (2025)

Taming the Titans: A Survey of Efficient LLM Inference Serving
by: Zhen, Ranran, et al.
Published: (2025)

Dynamic Vocabulary Pruning in Early-Exit LLMs
by: Vincenti, Jort, et al.
Published: (2024)

HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval
by: Park, Sungho, et al.
Published: (2026)

Transformers with Selective Access to Early Representations
by: Gunasekaran, Skye, et al.
Published: (2026)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
by: Taniguchi, Rei, et al.
Published: (2026)

MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models
by: Yu, Zichun, et al.
Published: (2024)

Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference
by: Qin, Zongyue, et al.
Published: (2024)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
by: Yang, Rubing, et al.
Published: (2025)

FlexLLM: Token-Level Co-Serving of LLM Inference and Finetuning with SLO Guarantees
by: Oliaro, Gabriele, et al.
Published: (2024)

CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
by: He, Junhui, et al.
Published: (2024)

The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs
by: Baidya, Avinash, et al.
Published: (2025)

Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction
by: Qiu, Haoran, et al.
Published: (2024)

DEL: Context-Aware Dynamic Exit Layer for Efficient Self-Speculative Decoding
by: Zarch, Hossein Entezari, et al.
Published: (2025)

APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
by: Zhao, Bowen, et al.
Published: (2024)

Dynamic Rebatching for Efficient Early-Exit Inference with DREX
by: Liu, Xuting, et al.
Published: (2025)

EE-Tuning: An Economical yet Scalable Solution for Tuning Early-Exit Large Language Models
by: Pan, Xuchen, et al.
Published: (2024)

One Jump Is All You Need: Short-Cutting Transformers for Early Exit Prediction with One Jump to Fit All Exit Levels
by: Seshadri, Amrit Diggavi
Published: (2025)

GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems
by: Wawdhane, Sourish, et al.
Published: (2026)

An Efficient Inference Framework for Early-exit Large Language Models
by: Miao, Ruijie, et al.
Published: (2024)

CHAI: Clustered Head Attention for Efficient LLM Inference
by: Agarwal, Saurabh, et al.
Published: (2024)

Progressive Mixed-Precision Decoding for Efficient LLM Inference
by: Chen, Hao Mark, et al.
Published: (2024)

Continuous Semantic Caching for Low-Cost LLM Serving
by: Atalar, Baran, et al.
Published: (2026)

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
by: Nagle, Alliot, et al.
Published: (2026)

Attractor Patch Networks: Reducing Catastrophic Forgetting with Routed Low-Rank Patch Experts
by: Shashank
Published: (2026)

Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion
by: Zaman, Kerem, et al.
Published: (2023)

Efficient Continual Pre-training of LLMs for Low-resource Languages
by: Nag, Arijit, et al.
Published: (2024)

Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution
by: Xu, Yechen, et al.
Published: (2024)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
by: Ma, Xuezhe, et al.
Published: (2024)