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.

Automatically optimize inference throughput v1.0.0

Use this resource to automatically speed up LLM inference on AMD Instinct GPUs within a given time budget

New

  • 583 downloads
  • 141 likes
  • 182 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install inference-throughput-auto-optimizer

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 Hyperloom wheel, runs the setup, then hands the run to the right skill. Hyperloom tests each lever (serving parameters and environment, framework patches, kernel rewrites), benchmarks every candidate and returns the optimization stack that produced the gain.

Mostly picked by

Updated November 2, 2026

Card for the “Automatically optimize inference throughput” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: workspace check, installation and handoff to the run phase
  • evals/machine.yml and skill-card.md: test configuration and skill card

Good fit for

  • A model served on MI300X or MI355X must get faster
  • You want a measured throughput gain, not an estimate

Not for

    Tags

    • throughput
    • vllm
    • amd gpu

    About

    You say

    “Optimize vLLM throughput on MI300X with a two-hour budget.”

    Card for the “Automatically optimize inference throughput” skill

    Skill published by amd 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 automatically speed up LLM inference on AMD Instinct GPUs within a given time budget
    3. Review and adjust the result

    Content preview

    Files

    • .federated.json0.3 KB
    • evals/evals.json4.3 KB
    • evals/machine.yml0.3 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • skill-card.md0.5 KB
    • SKILL.md6.7 KB

    Origin and licence

    Listed unmodified

    Author
    amd
    Source
    github.com/amd/skills/tree/0b64b9c4decd14af2e9789f1ef4c1b66909e68b1/skills/hyperloom-workload-optimizer
    Licence
    MIT

    Notice

    « hyperloom-workload-optimizer » (amd, 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.