​This is a hands-on, full-day workshop where you'll go from zero to running open-source models directly inside your Go applications — no cloud APIs, no external servers, and no data leaving your machine.

​The workshop is part of the GopherCamp conference program, but requires a separate workshop ticket in addition to the conference pass.

​Getting Started

​You'll start by:

• ​Loading a model

• ​Running your first inference with the Kronk SDK

​Configuring for Performance

​Then you'll learn how to configure models for your hardware:

• ​GPU layers

• ​KV cache placement

• ​Batch sizes

• ​Context windows

​So you get the best performance out of whatever machine you're running on.

​Controlling Model Output

​With the model tuned, you'll take control of its output through sampling parameters:

• ​Temperature

• ​Top-k

• ​Top-p

• ​Repetition penalties

• ​Grammar constraints that guarantee structured JSON responses

​High-Performance Caching

​Next, you'll see how Kronk's caching systems work:

• ​System Prompt Cache (SPC)

• ​Incremental Message Cache (IMC)

​These eliminate redundant computation and make multi-turn conversations fast.

​You'll watch a conversation go from full prefill on every request to only processing the newest message.

​Building Real Applications

​With the foundation solid, you'll build real applications:

​Retrieval-Augmented Generation (RAG)

​A RAG pipeline that grounds model responses in your own documents using embeddings and vector search.

​Natural Language → SQL

​A system where the model generates database queries from plain English — with grammar constraints ensuring the output is always valid, executable SQL.

​End-to-End Progression

​Each part builds on the last.

​By the end of the day, you won't just understand how private AI works — you'll have built applications that:

• ​Load models

• ​Cache intelligently

• ​Retrieve context

• ​Generate code

​All running locally on your own hardware.

​Find more about he workshop at:  https://github.com/ardanlabs/kronk

​Workshop Leader

​This workshop is led by William Kennedy, Managing Partner at Ardan Labs in Miami, Florida. William travels from the United States to deliver this workshop, building on the positive reception of his workshop last year.

​Ardan Labs is a group of passionate engineers, artists, and business professionals focused on building and delivering reliable, secure, and scalable solutions.

​William is the author of Go in Action and the Ultimate Go Notebook, and has written over 100 blog posts and articles about Go. He is also a founding member of GoBridge and the GDN, organizations dedicated to increasing Go adoption through diversity.

​With years of experience teaching and building production systems in Go, William brings deep technical expertise and practical insight to this hands-on workshop.