Accelerating and Securing AI Infrastructure
ABOUT THIS EVENT
🚀 Join us at WSO2 LLC office Austin for Food, Drinks, and Kubernetes on Thursday, November 19, 2026!
Everyone is welcome whether you are new to cloud native engineering or already experienced, come connect with the Austin cloud native community. We'll share the latest updates, practical insights, and real world learnings from AI, Kubernetes, CNCF projects, and modern platform engineering.
Featured Talk
🎤 Vamshidher Reddy Who Wrote That Admission Rule? Provenance and Authority for Kubernetes Policy
🎤 Vishwa Hiren Gandhi Reduce vLLM Pod Cold Starts with KServe Kernel Caching
Expect good conversations, practical takeaways, food, drinks, and a strong community vibe.
📍 Venue WSO2 LLC 10900 Stonelake Blvd Bldg 2, Suite 100, Austin, TX 78759
Arrival Instructions Upon arrival at the WeWork building, please proceed to 2nd Floor.
Parking Easy parking in front of the WeWork space
🤖 Sponsored by Cast AI Thank you to Cast AI for sponsoring Cloud Native Austin! Cast AI is the Kubernetes automation platform that keeps application performance and cloud costs on autopilot. It continuously analyzes how workloads actually behave and automatically tunes CPU, memory, and infrastructure provisioning — cutting cloud spend without hand-tuning your clusters. Learn more at https://cast.ai/
🏢 Venue Sponsored by WSO2 LLC Thank you to WSO2 for sponsoring Cloud Native Austin! WSO2 is an open-source AI platform company that helps organizations build, integrate, and secure applications and AI agents. Their commitment to open source and community support helps bring people together to learn, share, and innovate. Learn more: https://wso2.com/
Sponsored by Ardan Labs Thank you to Ardan Labs for sponsoring Cloud Native Austin!
Looking forward to seeing you there!
AGENDA
6:30 PM to 7.15 PM— Who Wrote That Admission Rule? Provenance and Authority for Kubernetes Policy In-Person · Vamshidher Reddy A benchmark and live demo show how provenance hashes and principal authority checks prevent poisoned Kubernetes and Terraform policies, including compilation to ValidatingAdmissionPolicy.
7:15 PM to 8.00 PM— Reduce vLLM Pod Cold Starts with KServe Kernel Caching In-Person · Vishwa Hiren Gandhi What is causing slow cold starts in Kubernetes-based LLM serving systems beyond model loading? In Kubernetes-based LLM serving, we often blame cold starts entirely on model loading. In reality, a large part of the delay comes from GPU kernel compilation. Even with model weights cached, kernels are recompiled from scratch on every new pod, even on every pod restart In this talk, we share a practical KServe-based solution that captures the compiled GPU kernels during the initial cold start, stores them as signed OCI artifacts, and caches them alongside the LLMInferenceService. New pods can then load these pre-compiled kernels at runtime, skipping redundant compilation during scale-out. In our tests under burst traffic, this approach reduced vLLM pod readiness time by 30–70%, depending on model size and GPU type.
