A Survey of Resource-efficient LLM and Multimodal Foundation Models

TL;DR

This survey reviews recent advances in resource-efficient large foundation models, highlighting algorithmic and systemic strategies to reduce hardware costs while maintaining performance in LLMs and multimodal models.

Contribution

It provides a comprehensive analysis of current resource-efficient methods across architectures, training, serving, and system design for large foundation models.

Findings

Summarizes key resource-efficient techniques in model architectures and training.

Analyzes systemic approaches for scalable deployment.

Identifies gaps and future directions in resource-efficient modeling.

Abstract

Large foundation models, including large language models (LLMs), vision transformers (ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine learning lifecycle, from training to deployment. However, the substantial advancements in versatility and performance these models offer come at a significant cost in terms of hardware resources. To support the growth of these large models in a scalable and environmentally sustainable way, there has been a considerable focus on developing resource-efficient strategies. This survey delves into the critical importance of such research, examining both algorithmic and systemic aspects. It offers a comprehensive analysis and valuable insights gleaned from existing literature, encompassing a broad array of topics from cutting-edge model architectures and training/serving algorithms to practical system designs and implementations. The goal of this survey is to provide an overarching understanding of how current approaches are tackling the resource challenges posed by large foundation models and to potentially inspire future breakthroughs in this field.