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.

LLM inference autoscaling with KEDA v1.0.0

Use this resource to autoscale LLM inference on Kubernetes automatically

New

  • 549 downloads
  • 183 likes
  • 122 saves

Free

Install with the CLI

In a terminal, from the folder you want:

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

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 NVIDIA GPU Operator, deploys vLLM pods with GPU resources, then configures KEDA on Prometheus metrics or a Redis queue, with a mix of on-demand and spot GPUs. You get autoscaling manifests and a cost strategy.

Mostly picked by

Updated November 2, 2026

Card for the “LLM inference autoscaling with KEDA” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: NVIDIA GPU Operator, vLLM deployment and KEDA autoscaling on Prometheus metrics
  • SKILL.md: Redis queue scaling, ScaledJob for batch inference and mixed spot node pool

Good fit for

  • Traffic to your LLM API is unpredictable and capacity must follow the load
  • You want to cut the GPU bill with spot instances

Not for

    Tags

    • llm
    • autoscaling
    • keda
    • gpu
    • kubernetes

    About

    You say

    “Set up KEDA autoscaling for our vLLM service based on the request queue length.”

    Card for the “LLM inference autoscaling with KEDA” skill

    Skill published by bagelhole 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 LLM inference on Kubernetes automatically
    3. Review and adjust the result

    Content preview

    Files

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

    Origin and licence

    Listed unmodified

    Author
    bagelhole
    Source
    github.com/bagelhole/devops-security-agent-skills/tree/0365f57a079b1332f95cf26e31dd2d5332a8399f/infrastructure/local-ai/llm-inference-scaling
    Licence
    MIT

    Notice

    « llm-inference-scaling » (bagelhole, 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.