Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices
- URL: http://arxiv.org/abs/2406.03777v3
- Date: Wed, 02 Oct 2024 04:14:21 GMT
- Title: Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices
- Authors: Ruiyang Qin, Dancheng Liu, Chenhui Xu, Zheyu Yan, Zhaoxuan Tan, Zhenge Jia, Amir Nassereldine, Jiajie Li, Meng Jiang, Ahmed Abbasi, Jinjun Xiong, Yiyu Shi,
- Abstract summary: We study how a resource-constrained computing environment would affect the design choices for a personalized LLM.
We consider the tradeoffs among a number of key design factors and their intertwined impacts on learning efficiency and accuracy.
- Score: 32.61693246340064
- License:
- Abstract: The scaling laws have become the de facto guidelines for designing large language models (LLMs), but they were studied under the assumption of unlimited computing resources for both training and inference. As LLMs are increasingly used as personalized intelligent assistants, their customization (i.e., learning through fine-tuning) and deployment onto resource-constrained edge devices will become more and more prevalent. An urging but open question is how a resource-constrained computing environment would affect the design choices for a personalized LLM. We study this problem empirically in this work. In particular, we consider the tradeoffs among a number of key design factors and their intertwined impacts on learning efficiency and accuracy. The factors include the learning methods for LLM customization, the amount of personalized data used for learning customization, the types and sizes of LLMs, the compression methods of LLMs, the amount of time afforded to learn, and the difficulty levels of the target use cases. Through extensive experimentation and benchmarking, we draw a number of surprisingly insightful guidelines for deploying LLMs onto resource-constrained devices. For example, an optimal choice between parameter learning and RAG may vary depending on the difficulty of the downstream task, the longer fine-tuning time does not necessarily help the model, and a compressed LLM may be a better choice than an uncompressed LLM to learn from limited personalized data.
Related papers
- LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.
LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.
Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
arXiv Detail & Related papers (2025-02-15T02:55:22Z) - Federated In-Context LLM Agent Learning [3.4757641432843487]
Large Language Models (LLMs) have revolutionized intelligent services by enabling logical reasoning, tool use, and interaction with external systems as agents.
In this paper, we propose a novel privacy-preserving Federated In-context LLM Agent Learning (FICAL) algorithm.
The results show that FICAL has competitive performance compared to other SOTA baselines with a significant communication cost decrease of $mathbf3.33times105$ times.
arXiv Detail & Related papers (2024-12-11T03:00:24Z) - Towards Robust Evaluation of Unlearning in LLMs via Data Transformations [17.927224387698903]
Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents.
In recent times research in the area of Machine Unlearning (MUL) has become active.
Main idea is to force LLMs to forget (unlearn) certain information (e.g., PII) without suffering from performance loss on regular tasks.
arXiv Detail & Related papers (2024-11-23T07:20:36Z) - zsLLMCode: An Effective Approach for Functional Code Embedding via LLM with Zero-Shot Learning [6.976968804436321]
Large language models (LLMs) have the capability of zero-shot learning, which does not require training or fine-tuning.
We propose zsLLMCode, a novel approach that generates functional code embeddings using LLMs.
arXiv Detail & Related papers (2024-09-23T01:03:15Z) - LLM-PBE: Assessing Data Privacy in Large Language Models [111.58198436835036]
Large Language Models (LLMs) have become integral to numerous domains, significantly advancing applications in data management, mining, and analysis.
Despite the critical nature of this issue, there has been no existing literature to offer a comprehensive assessment of data privacy risks in LLMs.
Our paper introduces LLM-PBE, a toolkit crafted specifically for the systematic evaluation of data privacy risks in LLMs.
arXiv Detail & Related papers (2024-08-23T01:37:29Z) - Performance Law of Large Language Models [58.32539851241063]
Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources.
Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources without extensive experiments.
arXiv Detail & Related papers (2024-08-19T11:09:12Z) - CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models [68.64605538559312]
In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives.
Inspired by our findings, we propose a measurement to quantitatively evaluate the learning balance.
In addition, we introduce an auxiliary loss regularization method to promote updating of the generation distribution of MLLMs.
arXiv Detail & Related papers (2024-07-29T23:18:55Z) - One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs)
We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
arXiv Detail & Related papers (2024-05-30T03:44:54Z) - Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models [11.845239346943067]
parameter-efficient fine-tuning (PEFT) is a promising approach to efficiently specialize large language models (LLMs) to task-specific data.
Our study highlights the potential for tuning larger LLMs and significant reductions in memory usage by combining PEFT with quantization.
arXiv Detail & Related papers (2023-08-21T04:31:06Z) - LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
Large language models (LLMs) have shown remarkable capabilities in language understanding and generation.
We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset.
Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
arXiv Detail & Related papers (2023-05-19T12:10:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.