Skip to content
conftrace_
2025 ICML ICML 2025

Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication Overlapping

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Muru Zhang, Mayank Mishra, Zhongzhu Zhou, William Brandon, Jue Wang, Yoon Kim, Jonathan Ragan-Kelley, Shuaiwen Leon Song, Ben Athiwaratkun, Tri Dao

Topics

Machine Learning > Application Areas > Efficient Computing Deep Learning > Techniques > Model Architecture

Keywords

model architecture efficient inference model parallelism distributed computing
Download PDF