# TrimCaching: Parameter-sharing Edge Caching for AI Model Downloading

arXiv: https://arxiv.org/abs/2404.14204 · HTML: https://mlsanity.com/paper/2404.14204/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2024.

## Built on by (most cited first, 11 of 11)

- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models](https://mlsanity.com/paper/2407.00952/) (2024)
- [AgentsCoMerge: Large Language Model Empowered Collaborative Decision Making for Ramp Merging](https://mlsanity.com/paper/2408.03624/) (2024)
- [CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perception](https://mlsanity.com/paper/2412.12000/) (2024)
- [TrimCaching: Parameter-sharing AI Model Caching in Wireless Edge Networks](https://mlsanity.com/paper/2405.03990/) (2024)
- [SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference](https://mlsanity.com/paper/2507.06567/) (2025)
- [PartialLoading: User Scheduling and Bandwidth Allocation for Parameter-sharing Edge Inference](https://mlsanity.com/paper/2503.22982/) (2025)
- [Channel-Aware Throughput Maximization for Cooperative Data Fusion in CAV](https://mlsanity.com/paper/2410.04320/) (2024)
- [Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edge](https://mlsanity.com/paper/2504.03718/) (2025)
- [BALANCE: Hybrid Autoregressive-Speculative LLM Inference at the Network Edge](https://mlsanity.com/paper/2608.05926/) (2026)
- [Space Generative AI with Solar Energy Harvesting](https://mlsanity.com/paper/2609.01062/) (2026)

## Abstract (arXiv)

Next-generation mobile networks are expected to facilitate fast AI model downloading to end users. By caching models on edge servers, mobile networks can deliver models to end users with low latency, resulting in a paradigm of edge model caching. In this paper, we develop a novel model placement framework, called parameter-sharing model caching (TrimCaching). TrimCaching exploits the key observation that a wide range of AI models, such as convolutional neural networks or large language models, can share a significant proportion of parameter blocks containing reusable knowledge, thereby improving storage efficiency. To this end, we formulate a parameter-sharing model placement problem to maximize the cache hit ratio in multi-edge wireless networks by balancing the fundamental tradeoff between storage efficiency and service latency. We show that the formulated problem is a submodular maximization problem with submodular constraints, for which no polynomial-time approximation algorithm exists. To tackle this challenge, we study an important special case, where a small fixed number of parameter blocks are shared across models, which often holds in practice. In such a case, a polynomial-time algorithm with a left(1-εright)/2-approximation guarantee is developed. Subsequently, we address the original problem for the general case by developing a greedy algorithm. Simulation results demonstrate that the proposed TrimCaching framework significantly improves the cache hit ratio compared with state-of-the-art content caching without exploiting shared parameters in AI models.