Self-Scaling LLM Infrastructure Powered by Rancher by ademicev0

Self-Scaling LLM Infrastructure Powered by Rancher

---

Description

The Problem

Running LLMs can get expensive and complex pretty quickly.

Today there are typically two choices:

1. Use cloud APIs like OpenAI or Anthropic. Easy to start with, but costs add up at scale.
2. Self-host everything - set up Kubernetes, figure out GPU scheduling, handle scaling, manage model serving... it's a lot of work.

What if there was a middle ground?

What if infrastructure scaled itself instead of making you scale it?

Can we use existing Rancher capabilities like CAPI, autoscaling, and GitOps to make this simpler instead of building everything from scratch?

Project Repository: github.com/alexander-demicev/llmserverless

---

What This Project Does

A key feature is hybrid deployment: requests can be routed based on complexity or privacy needs. Simple or low-sensitivity queries can use public APIs (like OpenAI), while complex or private requests are handled in-house on local infrastructure. This flexibility allows balancing cost, privacy, and performance - using cloud for routine tasks and on-premises resources for sensitive or demanding workloads.

A complete, self-scaling LLM infrastructure that:

• Scales to zero when idle (no idle costs)
• Scales up automatically when requests come in
• Adds more nodes when needed, removes them when demand drops
• Runs on any infrastructure - laptop, bare metal, or cloud

Think of it as "serverless for LLMs" - focus on building, the infrastructure handles itself.

How It Works

A combination of open source tools working together:

Flow:

• Users interact with OpenWebUI (chat interface)
• Requests go to LiteLLM Gateway
• LiteLLM routes requests to:
  • Ollama (Knative) for local model inference (auto-scales pods)
  • Or cloud APIs for fallback

---

Exploring Modern AI Trends and Kubernetes-Based AI Infrastructure by jluo

Description

Build a solid understanding of the current landscape of Artificial Intelligence and how modern cloud-native technologies—especially Kubernetes—support AI workloads.

Goals

Use Gemini Learning Mode to guide the exploration, surface relevant concepts, and structure the learning journey:

• Gain insight into the latest AI trends, tools, and architectural concepts.
• Understand how Kubernetes and related cloud-native technologies are used in the AI ecosystem (model training, deployment, orchestration, MLOps).

Resources

• Red Hat AI Topic Articles

  • https://www.redhat.com/en/topics/ai

• Kubeflow Documentation

  • https://www.kubeflow.org/docs/

• Q4 2025 CNCF Technology Landscape Radar report:

  • https://www.cncf.io/announcements/2025/11/11/cncf-and-slashdata-report-finds-leading-ai-tools-gaining-adoption-in-cloud-native-ecosystems/
  • https://www.cncf.io/wp-content/uploads/2025/11/cncfreporttechradar_111025a.pdf

• Agent-to-Agent (A2A) Protocol

  • https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/

---

A CLI for Harvester by mohamed.belgaied

Harvester does not officially come with a CLI tool, the user is supposed to interact with Harvester mostly through the UI. Though it is theoretically possible to use kubectl to interact with Harvester, the manipulation of Kubevirt YAML objects is absolutely not user friendly. Inspired by tools like multipass from Canonical to easily and rapidly create one of multiple VMs, I began the development of Harvester CLI. Currently, it works but Harvester CLI needs some love to be up-to-date with Harvester v1.0.2 and needs some bug fixes and improvements as well.

Project Description

Harvester CLI is a command line interface tool written in Go, designed to simplify interfacing with a Harvester cluster as a user. It is especially useful for testing purposes as you can easily and rapidly create VMs in Harvester by providing a simple command such as: harvester vm create my-vm --count 5 to create 5 VMs named my-vm-01 to my-vm-05.

Harvester CLI is functional but needs a number of improvements: up-to-date functionality with Harvester v1.0.2 (some minor issues right now), modifying the default behaviour to create an opensuse VM instead of an ubuntu VM, solve some bugs, etc.

Github Repo for Harvester CLI: https://github.com/belgaied2/harvester-cli

Done in previous Hackweeks

• Create a Github actions pipeline to automatically integrate Harvester CLI to Homebrew repositories: DONE
• Automatically package Harvester CLI for OpenSUSE / Redhat RPMs or DEBs: DONE

Goal for this Hackweek

The goal for this Hackweek is to bring Harvester CLI up-to-speed with latest Harvester versions (v1.3.X and v1.4.X), and improve the code quality as well as implement some simple features and bug fixes.

Some nice additions might be: * Improve handling of namespaced objects * Add features, such as network management or Load Balancer creation ? * Add more unit tests and, why not, e2e tests * Improve CI * Improve the overall code quality * Test the program and create issues for it

Issue list is here: https://github.com/belgaied2/harvester-cli/issues

Resources

The project is written in Go, and using client-go the Kubernetes Go Client libraries to communicate with the Harvester API (which is Kubernetes in fact). Welcome contributions are:

• Testing it and creating issues
• Documentation
• Go code improvement

What you might learn

Harvester CLI might be interesting to you if you want to learn more about:

• GitHub Actions
• Harvester as a SUSE Product
• Go programming language
• Kubernetes API
• Kubevirt API objects (Manipulating VMs and VM Configuration in Kubernetes using Kubevirt)

---

The Agentic Rancher Experiment: Do Androids Dream of Electric Cattle? by moio

Rancher is a beast of a codebase. Let's investigate if the new 2025 generation of GitHub Autonomous Coding Agents and Copilot Workspaces can actually tame it.

---

The Plan

Create a sandbox GitHub Organization, clone in key Rancher repositories, and let the AI loose to see if it can handle real-world enterprise OSS maintenance - or if it just hallucinates new breeds of Kubernetes resources!

Specifically, throw "Agentic Coders" some typical tasks in a complex, long-lived open-source project, such as:

❥ The Grunt Work: generate missing GoDocs, unit tests, and refactorings. Rebase PRs.

❥ The Complex Stuff: fix actual (historical) bugs and feature requests to see if they can traverse the complexity without (too much) human hand-holding.

❥ Hunting Down Gaps: find areas lacking in docs, areas of improvement in code, dependency bumps, and so on.

If time allows, also experiment with Model Context Protocol (MCP) to give agents context on our specific build pipelines and CI/CD logs.

Why?

We know AI can write "Hello World." and also moderately complex programs from a green field. But can it rebase a 3-month-old PR with conflicts in rancher/rancher? I want to find the breaking point of current AI agents to determine if and how they can help us to reduce our technical debt, work faster and better. At the same time, find out about pitfalls and shortcomings.

The CONCLUSION!!!

A State of the Union document was compiled to summarize lessons learned this week. For more gory details, just read on the diary below!

---

Preparing KubeVirtBMC for project transfer to the KubeVirt organization by zchang

Description

KubeVirtBMC is preparing to transfer the project to the KubeVirt organization. One requirement is to enhance the modeling design's security. The current v1alpha1 API (the VirtualMachineBMC CRD) was designed during the proof-of-concept stage. It's immature and inherently insecure due to its cross-namespace object references, exposing security concerns from an RBAC perspective.

The other long-awaited feature is the ability to mount virtual media so that virtual machines can boot from remote ISO images.

Goals

1. Deliver the v1beta1 API and its corresponding controller implementation
2. Enable the Redfish virtual media mount function for KubeVirt virtual machines

Resources

• The KubeVirtBMC repo: https://github.com/starbops/kubevirtbmc
• The new v1beta1 API: https://github.com/starbops/kubevirtbmc/issues/83
• Redfish virtual media mount: https://github.com/starbops/kubevirtbmc/issues/44

---

AI-Powered Unit Test Automation for Agama by joseivanlopez

The Agama project is a multi-language Linux installer that leverages the distinct strengths of several key technologies:

• Rust: Used for the back-end services and the core HTTP API, providing performance and safety.
• TypeScript (React/PatternFly): Powers the modern web user interface (UI), ensuring a consistent and responsive user experience.
• Ruby: Integrates existing, robust YaST libraries (e.g., yast-storage-ng) to reuse established functionality.

The Problem: Testing Overhead

Developing and maintaining code across these three languages requires a significant, tedious effort in writing, reviewing, and updating unit tests for each component. This high cost of testing is a drain on developer resources and can slow down the project's evolution.

The Solution: AI-Driven Automation

This project aims to eliminate the manual overhead of unit testing by exploring and integrating AI-driven code generation tools. We will investigate how AI can:

1. Automatically generate new unit tests as code is developed.
2. Intelligently correct and update existing unit tests when the application code changes.

By automating this crucial but monotonous task, we can free developers to focus on feature implementation and significantly improve the speed and maintainability of the Agama codebase.

Goals

• Proof of Concept: Successfully integrate and demonstrate an authorized AI tool (e.g., gemini-cli) to automatically generate unit tests.
• Workflow Integration: Define and document a new unit test automation workflow that seamlessly integrates the selected AI tool into the existing Agama development pipeline.
• Knowledge Sharing: Establish a set of best practices for using AI in code generation, sharing the learned expertise with the broader team.

Contribution & Resources

We are seeking contributors interested in AI-powered development and improving developer efficiency. Whether you have previous experience with code generation tools or are eager to learn, your participation is highly valuable.

If you want to dive deep into AI for software quality, please reach out and join the effort!

• Authorized AI Tools: Tools supported by SUSE (e.g., gemini-cli)
• Focus Areas: Rust, TypeScript, and Ruby components within the Agama project.

Interesting Links

• goose

---

Looking at Rust if it could be an interesting programming language by jsmeix

Get some basic understanding of Rust security related features from a general point of view.

This Hack Week project is not to learn Rust to become a Rust programmer. This might happen later but it is not the goal of this Hack Week project.

The goal of this Hack Week project is to evaluate if Rust could be an interesting programming language.

An interesting programming language must make it easier to write code that is correct and stays correct when over time others maintain and enhance it than the opposite.

---

Mail client with mailing list workflow support in Rust by acervesato

Description

To create a mail user interface using Rust programming language, supporting mailing list patches workflow. I know, aerc is already there, but I would like to create something simpler, without integrated protocols. Just a plain user interface that is using some crates to read and create emails which are fetched and sent via external tools.

I already know Rust, but not the async support, which is needed in this case in order to handle events inside the mail folder and to send notifications.

Goals

• simple user interface in the style of aerc, with some vim keybindings for motions and search
• automatic run of external tools (like mbsync) for checking emails
• automatic run commands for notifications
• apply patch set from ML
• tree-sitter support with styles

Resources

• ratatui: user interface (https://ratatui.rs/)
• notify: folder watcher (https://docs.rs/notify/latest/notify/)
• mail-parser: parser for emails (https://crates.io/crates/mail-parser)
• mail-builder: create emails in proper format (https://docs.rs/mail-builder/latest/mail_builder/)
• gitpatch: ML support (https://crates.io/crates/gitpatch)
• tree-sitter-rust: support for mail format (https://crates.io/crates/tree-sitter)

---

Learn how to use the Relm4 Rust GUI crate by xiaoguang_wang

Relm4 is based on gtk4-rs and compatible with libadwaita. The gtk4-rs crate provides all the tools necessary to develop applications. Building on this foundation, Relm4 makes developing more idiomatic, simpler, and faster.

https://github.com/Relm4/Relm4

---

Exploring Rust's potential: from basics to security by sferracci

Description

This project aims to conduct a focused investigation and practical application of the Rust programming language, with a specific emphasis on its security model. A key component will be identifying and understanding the most common vulnerabilities that can be found in Rust code.

Goals

Achieve a beginner/intermediate level of proficiency in writing Rust code. This will be measured by trying to solve LeetCode problems focusing on common data structures and algorithms. Study Rust vulnerabilities and learning best practices to avoid them.

Resources

Rust book: https://doc.rust-lang.org/book/

---