# The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks

arXiv: https://arxiv.org/abs/2505.09214 · HTML: https://mlsanity.com/paper/2505.09214/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 56 references that are in the map.
- First posted on arXiv 14 May 2025.

## Builds on (most cited first, 30 of 37)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Distributed Learning in Wireless Networks: Recent Progress and Future Challenges](https://mlsanity.com/paper/2104.02151/) (2021)
- [Layer-adaptive sparsity for the Magnitude-based Pruning](https://mlsanity.com/paper/2010.07611/) (2020)
- [Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities](https://mlsanity.com/paper/2405.10825/) (2024)
- [Nonlinear Transform Source-Channel Coding for Semantic Communications](https://mlsanity.com/paper/2112.10961/) (2021)
- [EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices](https://mlsanity.com/paper/2308.14352/) (2023)
- [Exploiting LLM Quantization](https://mlsanity.com/paper/2405.18137/) (2024)
- [Task-Oriented Communication for Multi-Device Cooperative Edge Inference](https://mlsanity.com/paper/2109.00172/) (2021)
- [Large Generative AI Models for Telecom: The Next Big Thing?](https://mlsanity.com/paper/2306.10249/) (2023)
- [M'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity](https://mlsanity.com/paper/2404.14527/) (2024)
- [Why Random Pruning Is All We Need to Start Sparse](https://mlsanity.com/paper/2210.02412/) (2022)
- [Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning](https://mlsanity.com/paper/1903.03472/) (2019)
- [A Survey on Collaborative DNN Inference for Edge Intelligence](https://mlsanity.com/paper/2207.07812/) (2022)
- [Resource Allocation for Multiuser Edge Inference with Batching and Early Exiting (Extended Version)](https://mlsanity.com/paper/2204.05223/) (2022)
- [Optimal Model Placement and Online Model Splitting for Device-Edge Co-Inference](https://mlsanity.com/paper/2105.13618/) (2021)
- [Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models](https://mlsanity.com/paper/2412.12687/) (2024)
- [Semantic Communications for Image Recovery and Classification via Deep Joint Source and Channel Coding](https://mlsanity.com/paper/2304.02317/) (2023)
- [Rethinking Resource Management in Edge Learning: A Joint Pre-training and Fine-tuning Design Paradigm](https://mlsanity.com/paper/2404.00836/) (2024)
- [Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach](https://mlsanity.com/paper/2406.02616/) (2024)
- [Calibration-Aided Edge Inference Offloading via Adaptive Model Partitioning of Deep Neural Networks](https://mlsanity.com/paper/2010.16335/) (2020)

## Built on by (most cited first, 7 of 7)

- [Empowering Intelligent Low-altitude Economy with Large AI Model Deployment](https://mlsanity.com/paper/2505.22343/) (2025)
- [FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding](https://mlsanity.com/paper/2601.00644/) (2026)
- [Quantization-Aware Collaborative Inference for Large Embodied AI Models](https://mlsanity.com/paper/2602.13052/) (2026)
- [Adversary-Aware Private Inference over Wireless Channels](https://mlsanity.com/paper/2510.20518/) (2025)
- [Closing the Generalization Gap in Parameter-efficient Federated Edge Learning](https://mlsanity.com/paper/2511.23282/) (2025)
- [Reinforcement learning with timed constraints for robotics motion planning](https://mlsanity.com/paper/2601.00087/) (2025)
- [Logit-Aware MIMO AirComp for Distributed Mixture-of-Experts LLM Inference over Wireless Edge Networks](https://mlsanity.com/paper/2610.03741/) (2026)

## Abstract (arXiv)

The growing demand for large artificial intelligence model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications. In particular, edge-device co-inference, which partitions LAIMs between edge devices and servers, has emerged as a promising strategy for resource-efficient LAIM execution in wireless networks. In this paper, we investigate a pruning-aware LAIM co-inference scheme, where a pre-trained LAIM is pruned and partitioned into on-device and on-server sub-models for deployment. For analysis, we first prove that the LAIM output distortion is upper bounded by its parameter distortion. Then, we derive a lower bound on parameter distortion via rate-distortion theory, analytically capturing the relationship between pruning ratio and co-inference performance. Next, based on the analytical results, we formulate an LAIM co-inference distortion bound minimization problem by jointly optimizing the pruning ratio, transmit power, and computation frequency under system latency, energy, and available resource constraints. Moreover, we propose an efficient algorithm to tackle the considered highly non-convex problem. Finally, extensive simulations demonstrate the effectiveness of the proposed design. In particular, model parameter distortion is shown to provide a reliable bound on output distortion. Also, the proposed joint pruning ratio and resource management design achieves superior performance in balancing trade-offs among inference performance, system latency, and energy consumption compared with benchmark schemes, such as fully on-device and on-server inference. Moreover, the split point is shown to play a critical role in system performance optimization under heterogeneous and resource-limited edge environments.