Accelerating and Securing AI Infrastructure
Hosted by CNCF Cloud Native Austin
Thursday, November 19, 2026 · 5:30pm · 10900 Stonelake Boulevard · hosted by CNCF Cloud Native Austin
about this room
Cloud Native Austin's monthly meetup brings a slice of KubeCon home for people who could not make the trip this year. It runs from 5:30pm to 8pm at the WSO2 office on Stonelake Boulevard in north Austin, with food and drinks laid on, and it is pitched at every experience level.
Two talks anchor the evening. Vamshidher Reddy covers provenance and authority for Kubernetes policy, and Vishwa Gandhi explains how KServe kernel caching cuts cold-start times for vLLM pods. Around them, expect updates on CNCF projects and plenty of chat about AI infrastructure and platform engineering. Cast AI sponsors the night, WSO2 provides the space and Ardan Labs is also listed as a sponsor.
if you run Kubernetes or serve models in production, the vLLM cold-start talk tackles a real cost and latency headache, and the people around you will be wrestling with the same stack.