Thursday July 30, 2026
1 PM ET / 10 AM PT
Kubernetes is already the default foundation for many production workloads, and an increasing number of teams are now adding LLM inference workloads to those same clusters. Inference traffic, though, brings different scaling signals, GPU requirements, and failure modes than typical web applications.
Join Fairwinds for a practical webinar: Running LLM Inference On Kubernetes: From Cluster To First Prompt.
We will cover:
How LLM inference traffic differs from standard Kubernetes workloads
What your cluster needs around scheduling, networking, resources, and scaling signals
A demo of an end‑to‑end inference path on Kubernetes
Platform engineers, DevOps leaders, SREs, and anyone responsible for managing Kubernetes infrastructure across teams or environments.
