Towards optimal scheduling of deep learning training jobs in GPU clusters
Deep Learning (DL) manifests as a groundbreaking technology, revolutionizing numerous fields. This paradigm shift has fueled an ever-growing demand for training DL models, leading to the development of hyperscale GPU clusters. Despite their massive computational power, these clusters often struggle...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Doctor of Philosophy |
| Language: | English |
| Published: |
Nanyang Technological University
2025
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/182633 |