264001
eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJid2V2ZW50cy1wdWJsaWMtYXBpIiwiYXVkIjpbInB1YmxpYy13ZWIiXSwic3ViIjoiaHR0cHM6Ly93d3cuZ29vZ2xlY2xvdWRldmVudHMuY29tIiwiaWF0IjoxNzc1NDE1MjA5LCJuYmYiOjE3NzU0MTUyMDksImV4cCI6MTc3NTQxODgwOSwiY29udGV4dCI6eyJwYXlsb2FkIjp7ImlkIjoiIiwicmVnVHlwZU5hbWUiOiIiLCJldmVudF9pZCI6IjI2NDAwMSIsImNfMzI5MDQxNiI6IiJ9fX0.Xqj4cjUH_BT57PmhKBGInSjC98kv2PVwxycWSWTSIg0
phase 5 session info modal
Day 1 – April 22, 2026
Lightning Talks
DEVLT-224 • Technical
Building an Agentic Platform using Ray Serve LLM and vLLM on GKE
location_on Developer Theater
schedule 4:00 PM - 4:25 PM

Discover how to deploy Qwen model on Google Kubernetes Engine (GKE) using Ray Serve and vLLM for high-throughput, low-latency inference. This session provides a guide to integrating an ADK agent for sophisticated chat and tool usage, leveraging TPU-enabled nodes for intensive workloads. Explore Ray native features for autoscaling and fault tolerance while gaining a blueprint to transform LLMs into dynamic "Agentic" systems - a key requirement for enterprises building next-generation AI applications.

 Read more
This agenda widget contains logic for handling same sessions available at multiple times
GTM Tracking Header name present
Session
contains logic for gtm tracking when modal open