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.

ML inference optimization v1.0.0

Use this resource to speed up the inference of a machine learning model

New

  • 320 downloads
  • 108 likes
  • 197 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install ml-inference-optimization

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 first sets a performance baseline, then proposes exports, compilation, quantization and Triton or batching settings. You get PyTorch to ONNX export patterns, a config.pbtxt setup and benchmark guidance.

Mostly picked by

Updated November 2, 2026

Card for the “ML inference optimization” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: benchmarking method and bottlenecks
  • SKILL.md: ONNX export, torch.compile and quantization
  • SKILL.md: Triton configuration, dynamic batching and GPU instances

Good fit for

  • Your model responds too slowly in production
  • Your inference GPU costs exceed the budget

Not for

    Tags

    • inference
    • onnx
    • quantization
    • triton

    About

    You say

    “Export my PyTorch model to ONNX and measure p95 latency before and after INT8 quantization.”

    Card for the “ML inference optimization” skill

    Skill published by josiahsiegel 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 speed up the inference of a machine learning model
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md9.1 KB

    Origin and licence

    Listed unmodified

    Author
    josiahsiegel
    Source
    github.com/josiahsiegel/claude-plugin-marketplace/tree/5a1b1123b9e50aa9a66a61005ca6fe012cc7442d/plugins/ml-master/skills/ml-inference-optimization
    Licence
    MIT

    Notice

    « ml-inference-optimization » (josiahsiegel, 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.