Explore how Google's Dynamic Workload Scheduler (DWS) addresses the growing demand for GPU capacity in AI/ML workloads in this informative video from Google Cloud Next 2024. Learn about the functionality of DWS, its compatibility with various workloads, and how to choose between different Compute Engine consumption models. Discover strategies for combining Compute Engine models, real-world applications, and steps to get started with DWS. Gain insights from Product Managers Laura Ionita and Ari Liberman as they discuss solutions for easy and affordable access to GPUs for AI/ML tasks, presented by host Debi Cabrera.
Easy and Affordable Access to GPUs for AI/ML Workloads - Dynamic Workload Scheduler
Overview
Syllabus
- Meet Laura and Ari
- What is Dynamic Workload Scheduler?
- Which workloads function with Dynamic Workload Scheduler?
- How to choose between Compute Engine models
- Combining different Compute Engine models
- Real world examples
- Get started with Dynamic Workload Scheduler
- Wrap up
Taught by
Google Cloud Tech
Related Courses
-
How to Get Easy and Affordable Access to GPUs for AI/ML Workloads
-
Accelerating AI Inference Workloads with Google Cloud TPUs and GPUs
-
AI Workloads and Hardware Accelerators - Introducing the Google Cloud AI Hypercomputer
-
Accelerate AI Inference Workloads with Google Cloud TPUs and GPUs
-
Accelerate AI Training Workloads with Google Cloud TPUs and GPUs
