Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Automatic LLM inference scaling on Kubernetes v1.0.0

Use this resource to autoscale an LLM inference cluster on Kubernetes

New

  • 547 downloads
  • 182 likes
  • 164 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-inference-autoscaling

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent installs the GPU operator, deploys vLLM with its GPU resources, then configures KEDA on Prometheus metrics or a Redis queue, with ScaledJob for batch work and a mix of on-demand and spot nodes. You get manifests to adapt and test.

Mostly picked by

Updated November 2, 2026

Card for the “Automatic LLM inference scaling on Kubernetes” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: prerequisites, GPU nodes and vLLM deployment
  • SKILL.md: KEDA autoscaling, queues, ScaledJob and spot instances

Good fit for

  • Your inference traffic varies a lot over the day
  • You want to cut GPU costs with spot instances

Not for

    Tags

    • kubernetes
    • llm
    • keda
    • gpu

    About

    You say

    “Set up KEDA autoscaling for my vLLM service on my Redis queue length, with spot nodes.”

    Card for the “Automatic LLM inference scaling on Kubernetes” skill

    Skill published by sickn33 under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to autoscale an LLM inference cluster on Kubernetes
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md8.9 KB

    Origin and licence

    Listed unmodified

    Author
    sickn33
    Source
    github.com/sickn33/agentic-awesome-skills/tree/e9809578fd426a284af017c5db99f8eb6628e6ca/skills/llm-inference-scaling
    Licence
    MIT

    Notice

    « llm-inference-scaling » (sickn33, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.