Over-Quota GPU Usage with Fairness and Preemption
See how NVIDIA Run:ai manages over-quota GPU usage while maintaining fairness and resource guarantees across clusters.
Note
This video was recorded using NVIDIA Run:ai version 2.25.9. The user interface, features, and workflows may differ in newer releases. For the latest information, refer to the current documentation.
What You’ll Learn:
- How teams can temporarily use extra GPU capacity when available
- How NVIDIA Run:ai restores fairness when guaranteed resources are needed
- How preemption works in shared GPU environments
- How over-quota scheduling helps maximize GPU utilization without compromising guarantees
Related Documentation:
Follow the validated quickstart in the product documentation: Over Quota, Fairness and Preemption