Cloud Technology

How are you optimizing Kubernetes GPU scheduling for LLM inference workloads in 2025?

BE Asked by Benjamin Carter · 14-03-2024
0 upvotes 14,350 views 0 comments
The question

We are moving our generative AI models from standalone instances to a shared Kubernetes cluster. I’m struggling with GPU fragmentation and underutilization. Is anyone using NVIDIA's Multi-Instance GPU (MIG) or specialized schedulers like KubeRay to handle the bursty nature of inference? How do you ensure low-latency responses when multiple pods are competing for the same hardware resources?

3 answers

0
JE
Answered on 12-06-2024

We’ve had great success using the NVIDIA GPU Operator alongside MIG. The biggest trick was not just enabling MIG, but setting up specific node pools with "Time-Slicing" for smaller dev models while reserving full A100/H100 slices for production inference. We also integrated the KEDA autoscaler to trigger scaling based on the number of pending requests in our model queue rather than just CPU/Memory metrics. This setup reduced our cold-start times by 30% and significantly improved our hardware ROI.

0
RO
Answered on 15-08-2025

Jessica, that KEDA approach sounds promising. Are you seeing any significant scheduling overhead or "noisy neighbor" issues when running different model versions on the same physical GPU?

CH 20-09-2025

Robert, we actually use Pod Anti-Affinity rules to ensure that high-priority inference pods never share a GPU with background batch processing tasks. For noisy neighbors, we rely on the GPU Operator’s device monitoring to kill any process that leaks memory or exceeds its allocated power limit, which keeps the node stable.

0
SA
Answered on 05-10-2025

We’ve found that using "PriorityClasses" is essential. It ensures our critical user-facing AI models always pre-empt lower-priority data cleaning jobs when GPU capacity gets tight.

BE 10-10-2025

Exactly. Without PriorityClasses, your production traffic is at the mercy of whatever job started first. It's a fundamental part of the 2025 AI-on-K8s playbook.

Share your thoughts

Your email address will not be published. Required fields are marked (*)

Professional Counselling Session

Still have questions?
Schedule a free counselling session

Our experts are ready to help you with any questions about courses, admissions, or career paths. Get personalized guidance from industry professionals.

Request a Call Back

Search Online

We Accept

We Accept

Follow Us

"PMI®", "PMBOK®", "PMP®", "CAPM®" and "PMI-ACP®" are registered marks of the Project Management Institute, Inc. | "CSM", "CST" are Registered Trade Marks of The Scrum Alliance, USA. | COBIT® is a trademark of ISACA® registered in the United States and other countries.

World globe icon Country: Canada

Book Free Session