Uploaded September 2026 | Updated November 2026, 4 days ago
Get more out of your LLM serving with Ray Serve on GKE.
At Ray Summit 2026, Seiji Eicher, Software Engineer at Anyscale, and Spencer Peterson, Software Engineer at Google, show how to configure the latest features end to end to maximize throughput, minimize latency, and stay on top of day-two operations: managing your RayServices, accelerators, and network ingress with Kubernetes and the Gateway API.
You'll leave with best practices for production LLM serving on GKE.
Liked this video? Check out other Ray Summit breakout session recordings: youtube.com/playlist?list=PLZNaJyYZRPdo
Subscribe to our YouTube channel to stay up-to-date on the future of AI: youtube.com/c/anyscale
🔗 Connect with us:
LinkedIn: linkedin.com/company/joinanyscale
X: https://x.com/anyscalecompute
Website: anyscale.com
Get more out of your LLM serving with Ray Serve on GKE.
At Ray Summit 2026, Seiji Eicher, Software Engineer at Anyscale, and Spencer Peterson, Software Engineer at Google, show how to configure the latest features end to end to maximize throughput, minimize latency, and stay on top of day-two operations: managing your RayServices, accelerators, and network ingress with Kubernetes and the Gateway API.
You'll leave with best practices for production LLM serving on GKE.
Liked this video? Check out other Ray Summit breakout session recordings: youtube.com/playlist?list=PLZNaJyYZRPdo
Subscribe to our YouTube channel to stay up-to-date on the future of AI: youtube.com/c/anyscale
🔗 Connect with us:
LinkedIn: linkedin.com/company/joinanyscale
X: https://x.com/anyscalecompute
Website: anyscale.com










