skills.rest
coreweave
coreweaveOFFICIAL
Explore all skills by this author →
WebsiteGitHub

upgrade-sunk

Automate SUNK deployment upgrades with Helm pre- and post-upgrade steps.

7|Updated Jul 9, 2026
Search Tags:#kubernetes#helm#upgrade#slurm#sunk
One-click install
npx skills add https://github.com/coreweave/sunk-anywhere --skill upgrade-sunk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: upgrade-sunk
Source: https://github.com/coreweave/sunk-anywhere/tree/main/skills/universal/upgrade-sunk
Command: npx skills add https://github.com/coreweave/sunk-anywhere --skill upgrade-sunk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the complex process of upgrading SUNK (Slurm on Kubernetes) deployments across various cloud providers, handling pre-upgrade backups, Helm upgrades, and post-upgrade fixes.

Core Features & Use Cases

  • Pre-upgrade Checks: Ensures cluster health and configuration integrity before upgrade.
  • Helm Upgrade Execution: Upgrades SUNK deployment using Helm, managing all necessary chart configurations.
  • Post-upgrade Steps: Automates post-upgrade configuration fixes, including re-patching gres.conf, system tolerations, and GPU pod restarts.
  • Use Case: Ideal for upgrading SUNK to the latest version in a production environment with multiple components and dependencies.

Quick Start

Run the upgrade-sunk skill to update your SUNK deployment.

Frequently Asked Questions about upgrade-sunk

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I upgrade Slurm on Kubernetes deployments using Helm?▼

Automating the SUNK upgrade process handles pre-upgrade cluster health checks, executes the Helm chart upgrade, and applies necessary post-upgrade configuration patches to maintain deployment integrity.

What post-upgrade steps are required for SUNK deployments?▼

Post-upgrade steps for SUNK deployments include re-patching the gres.conf file, updating system tolerations, and restarting GPU pods. Automating these steps ensures your Slurm on Kubernetes environment functions correctly after a Helm upgrade.

Why do I need pre-upgrade checks before updating Slurm on Kubernetes?▼

Pre-upgrade checks verify cluster health and configuration integrity before executing Helm upgrades, preventing potential deployment failures and configuration corruption in complex SUNK environments.

Can I use Helm to upgrade SUNK configurations across different cloud providers?▼

Yes, Helm manages SUNK chart upgrades across various cloud providers by standardizing the deployment update process and applying necessary post-upgrade configuration fixes like gres.conf re-patching.

What is the best way to automate gres.conf re-patching after a Kubernetes Slurm upgrade?▼

The best way to automate gres.conf re-patching after a Kubernetes Slurm upgrade is to use scripts designed for post-upgrade SUNK maintenance. This ensures GPU resources are correctly configured without manual intervention.

Related Skills

Explore More Software Engineering Skills→
coreweavecoreweave
7

deploy-sunk-on-gke

Automate SUNK deployment on Google Kubernetes Engine with cluster and Slurm setup.

Official
Advanced
dongzhuoyaodongzhuoyao
10

slurm-gpu-training

Submit GPU training jobs to Slurm clusters with preflight validation and monitoring.

Community
Advanced
coreweavecoreweave
7

deploy-sunk-on-kubernetes

Automate SUNK deployment on Kubernetes clusters with Helm and storage configuration.

Official
Advanced
moogieonmoogieon

gstack-upgrade

Automate gstack upgrades to the latest version using Bash, Git, and Python scripts.

Community
Advanced