Designing Large Foundation Models for Efficient Training and Inference: A Survey

TMLR Paper4458 Authors

Abstract: This paper focuses on modern efficient training and inference technologies on foundation models and illustrates them from two perspectives: model and system design. Model and System Design optimize LLM training and inference from different aspects to save computational resources, making LLMs more efficient, affordable, and more accessible.

Submission Length: Long submission (more than 12 pages of main content)

Previous TMLR Submission Url: https://openreview.net/forum?id=qxFCyX4c0K

Changes Since Last Submission: This version of submission uses the default TMLR template, ensuring anonymity by removing the GitHub link in the abstract.

Assigned Action Editor: ~antonio_vergari2

Submission Number: 4458