Serverless GPUs in Production: How Cerebrium Built a Globally... Dave Protasowski & Elijah Roussos
About this talk
This talk presents an in-depth exploration of how Cerebrium utilizes Knative to create a serverless cloud platform that efficiently serves international customers with low latency and cost optimization. The speakers, Dave Protasowski and Elijah Roussos, discuss the challenges encountered across various operational environments and the innovative solutions implemented using Knative. They share key lessons learned from their firsthand experiences, providing practical insights into Knative’s operational strengths, real-world performance, and applicability in building an AI platform. This session offers valuable takeaways for those looking to optimize existing Knative deployments or seek inspiration for future projects.
More from this event
See all 436 talks →
Best of KubeCon + CloudNativeCon Amsterdam 2026
2:17
The Quiet Work of Forever: Sustaining Open Source Communities - O. Hope Amaechi-Okorie, JSON Schema
26:24
Evolving KServe: The Unified Model Inference Platform for Both Predictive and... F. Spolti & J. Lee
32:40
Preventing S3 Cost Storms: Applying Cortex’s Efficiency Lessons to I/O-Heav... A. Fishman-Lichterman
5:32