Kubernetes-Based ML Lifecycle Automation by lmiranda

Description

This project aims to build a complete end-to-end Machine Learning pipeline running entirely on Kubernetes, using Go, and containerized ML components.

The pipeline will automate the lifecycle of a machine learning model, including:

• Data ingestion/collection
• Model training as a Kubernetes Job
• Model artifact storage in an S3-compatible registry (e.g. Minio)
• A Go-based deployment controller that automatically deploys new model versions to Kubernetes using Rancher
• A lightweight inference service that loads and serves the latest model
• Monitoring of model performance and service health through Prometheus/Grafana

The outcome is a working prototype of an MLOps workflow that demonstrates how AI workloads can be trained, versioned, deployed, and monitored using the Kubernetes ecosystem.

Goals

By the end of Hack Week, the project should:

1. Produce a fully functional ML pipeline running on Kubernetes with:

   • Data collection job
   • Training job container
   • Storage and versioning of trained models
   • Automated deployment of new model versions
   • Model inference API service
   • Basic monitoring dashboards

2. Showcase a Go-based deployment automation component, which scans the model registry and automatically generates & applies Kubernetes manifests for new model versions.

3. Enable continuous improvement by making the system modular and extensible (e.g., additional models, metrics, autoscaling, or drift detection can be added later).

4. Prepare a short demo explaining the end-to-end process and how new models flow through the system.

Resources

Project Repository

Updates

1. Training pipeline and datasets
2. Inference Service py

---

Background Coding Agent by mmanno

Description

I had only bad experiences with AI one-shots. However, monitoring agent work closely and interfering often did result in productivity gains.

Now, other companies are using agents in pipelines. That makes sense to me, just like CI, we want to offload work to pipelines: Our engineering teams are consistently slowed down by "toil": low-impact, repetitive maintenance tasks. A simple linter rule change, a dependency bump, rebasing patch-sets on top of newer releases or API deprecation requires dozens of manual PRs, draining time from feature development.

So far we have been writing deterministic, script-based automation for these tasks. And it turns out to be a common trap. These scripts are brittle, complex, and become a massive maintenance burden themselves.

Can we make prompts and workflows smart enough to succeed at background coding?

Goals

We will build a platform that allows engineers to execute complex code transformations using prompts.

By automating this toil, we accelerate large-scale migrations and allow teams to focus on high-value work.

Our platform will consist of three main components:

• "Change" Definition: Engineers will define a transformation as a simple, declarative manifest:
  
  • The target repositories.
    
  • A wrapper to run a "coding agent", e.g., "gemini-cli".
    
  • The task as a natural language prompt.
    
• "Change" Management Service: A central service that orchestrates the jobs. It will receive Change definitions and be responsible for the job lifecycle.
  
• Execution Runners: We could use existing sandboxed CI runners (like GitHub/GitLab runners) to execute each job or spawn a container.

MVP

• Define the Change manifest format.
  
• Build the core Management Service that can accept and queue a Change.
• Connect management service and runners, dynamically dispatch jobs to runners.
• Create a basic runner script that can run a hard-coded prompt against a test repo and open a PR.
  

Stretch Goals:

• Multi-layered approach, Workflow Agents trigger Coding Agents:
  
  1. Workflow Agent: Gather information about the task interactively from the user.
     
  2. Coding Agent: Once the interactive agent has refined the task into a clear prompt, it hands this prompt off to the "coding agent." This background agent is responsible for executing the task and producing the actual pull request.
     
• Use MCP:
  
  1. Workflow Agent gathers context information from Slack, Github, etc.
     
  2. Workflow Agent triggers a Coding Agent.
     
• Create a "Standard Task" library with reliable prompts.
  1. Rebasing rancher-monitoring to a new version of kube-prom-stack
     
  2. Update charts to use new images
     
  3. Apply changes to comply with a new linter
     
  4. Bump complex Go dependencies, like k8s modules
     
  5. Backport pull requests to other branches
• Add “review agents” that review the generated PR.
  

See also

---

MCP Trace Suite by r1chard-lyu

Description

This project plans to create an MCP Trace Suite, a system that consolidates commonly used Linux debugging tools such as bpftrace, perf, and ftrace.

The suite is implemented as an MCP Server. This architecture allows an AI agent to leverage the server to diagnose Linux issues and perform targeted system debugging by remotely executing and retrieving tracing data from these powerful tools.

• Repo: https://github.com/r1chard-lyu/systracesuite
• Demo: Slides

Goals

1. Build an MCP Server that can integrate various Linux debugging and tracing tools, including bpftrace, perf, ftrace, strace, and others, with support for future expansion of additional tools.

2. Perform testing by intentionally creating bugs or issues that impact system performance, allowing an AI agent to analyze the root cause and identify the underlying problem.

Resources

• Gemini CLI: https://geminicli.com/
• eBPF: https://ebpf.io/
• bpftrace: https://github.com/bpftrace/bpftrace/
• perf: https://perfwiki.github.io/main/
• ftrace: https://github.com/r1chard-lyu/tracium/

---

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!

---

Try AI training with ROCm and LoRA by bmwiedemann

Description

I want to setup a Radeon RX 9600 XT 16 GB at home with ROCm on Slowroll.

Goals

I want to test how fast AI inference can get with the GPU and if I can use LoRA to re-train an existing free model for some task.

Resources

• https://rocm.docs.amd.com/en/latest/compatibility/compatibility-matrix.html
• https://build.opensuse.org/project/show/science:GPU:ROCm
• https://src.opensuse.org/ROCm/
• https://www.suse.com/c/lora-fine-tuning-llms-for-text-classification/

Results

got inference working with llama.cpp:

export LLAMACPP_ROCM_ARCH=gfx1200
HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
cmake -S . -B build -DGGML_HIP=ON -DAMDGPU_TARGETS=$LLAMACPP_ROCM_ARCH \
-DCMAKE_BUILD_TYPE=Release -DLLAMA_CURL=ON \
-Dhipblas_DIR=/usr/lib64/cmake/hipblaslt/ \
&& cmake --build build --config Release -j8
m=models/gpt-oss-20b-mxfp4.gguf
cd $P/llama.cpp && build/bin/llama-server --model $m --threads 8 --port 8005 --host 0.0.0.0 --device ROCm0 --n-gpu-layers 999

Without the --device option it faulted. Maybe because my APU also appears there?

I updated/fixed various related packages: https://src.opensuse.org/ROCm/rocm-examples/pulls/1 https://src.opensuse.org/ROCm/hipblaslt/pulls/1 SR 1320959

benchmark

I benchmarked inference with llama.cpp + gpt-oss-20b-mxfp4.gguf and ROCm offloading to a Radeon RX 9060 XT 16GB. I varied the number of layers that went to the GPU:

• 0 layers 14.49 tokens/s (8 CPU cores)
• 9 layers 17.79 tokens/s 34% VRAM
• 15 layers 22.39 tokens/s 51% VRAM
• 20 layers 27.49 tokens/s 64% VRAM
• 24 layers 41.18 tokens/s 74% VRAM
• 25+ layers 86.63 tokens/s 75% VRAM (only 200% CPU load)

So there is a significant performance-boost if the whole model fits into the GPU's VRAM.

---

Liz - Prompt autocomplete by ftorchia

Description

Liz is the Rancher AI assistant for cluster operations.

Goals

We want to help users when sending new messages to Liz, by adding an autocomplete feature to complete their requests based on the context.

Example:

• User prompt: "Can you show me the list of p"
• Autocomplete suggestion: "Can you show me the list of p...od in local cluster?"

Example:

• User prompt: "Show me the logs of #rancher-"
• Chat console: It shows a drop-down widget, next to the # character, with the list of available pod names starting with "rancher-".

Technical Overview

1. The AI agent should expose a new ws/autocomplete endpoint to proxy autocomplete messages to the LLM.
2. The UI extension should be able to display prompt suggestions and allow users to apply the autocomplete to the Prompt via keyboard shortcuts.

Resources

GitHub repository

---