OpenTechSummit India 2026

OpenTechSummit India 2026 is a one-day open technology and community event organized by FOSSASIA as part of Devcon 8, taking place at the Jio World Centre in Mumbai.

Talk: Prefill, Decode, and Despair: Disaggregated LLM Serving Made Boring

Sergey Pronin, Founder of Solanica · Thursday, November 5 · 1:15–1:30 PM IST · Main Stage

KServe can serve large language models on Kubernetes — but past “hello world,” it gets sharp. You face disaggregated prefill/decode, four kinds of parallelism, autoscaling that behaves differently under KEDA versus HPA, a CPU profile that runs out of memory before your model loads, and gateway wiring where one wrong setting silently breaks routing. Miss a field and you don’t get an error — you get a slow, wrong, or unreachable model.

This talk shows how OpenEverest’s KServe provider hides all of that behind a single, technology-agnostic Instance resource. In ten lines of YAML, you get an OpenAI-compatible endpoint. We’ll look at the real traps it saves you from: container args that silently drop your defaults, a gateway backend that bypasses request routing, and KV-cache settings that refuse to start.

See the talk in the schedule

Visit the OpenEverest project table

OpenEverest has a project table at OpenTechSummit India. Stop by to talk about running databases and AI workloads on Kubernetes, and learn how to get involved in the project.

Learn more about the conference.