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.

Serverless GPU workloads on Modal v1.0.0

Use this resource to run GPU workloads on Modal without managing servers

New

  • 404 downloads
  • 196 likes
  • 187 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install serverless-gpu-jobs-modal

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 analyzes the task, estimates its cost and picks a suitable GPU, then generates a Modal Python launcher. It declares dependencies in the code and starts the job with modal run. You get a runnable script and a cost estimate, with no server to manage.

Mostly picked by

Updated November 2, 2026

Card for the “Serverless GPU workloads on Modal” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: task analysis, cost estimate and GPU choice
  • SKILL.md: Modal launcher generation and cost comparison for 7-8B models

Good fit for

  • You need a GPU for a one-off training or inference job
  • You want to skip SSH and Docker to launch a compute job

Not for

    Tags

    • modal
    • gpu
    • serverless
    • training

    About

    You say

    “Run the fine-tuning of this 8B model on Modal, with a cost estimate before it starts.”

    Card for the “Serverless GPU workloads on Modal” skill

    Skill published by wanshuiyin 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 run GPU workloads on Modal without managing servers
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md12.9 KB

    Origin and licence

    Listed unmodified

    Author
    wanshuiyin
    Source
    github.com/wanshuiyin/auto-claude-code-research-in-sleep/tree/18bceb3c71c638bef58096274e1c9a6d323dbc0a/skills/serverless-modal
    Licence
    MIT

    Notice

    « serverless-modal » (wanshuiyin, 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.