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.

Writing GPU kernels with Triton v1.0.0

Use this resource to write Python GPU kernels with Triton and integrate them with PyTorch

New

  • 384 downloads
  • 132 likes
  • 131 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install triton-gpu-kernels

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 helps you write a Triton kernel with masked memory access, tune it with the autotuner, then measure it with triton.testing. It also shows how to wrap the kernel as a PyTorch custom op.

Mostly picked by

Updated November 2, 2026

Card for the “Writing GPU kernels with Triton” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: minimal kernel, masked loads and stores, atomic operations
  • SKILL.md: autotuning, performance measurement and PyTorch integration

Good fit for

  • You want to speed up a PyTorch operation without writing raw CUDA
  • You prototype a fused kernel such as softmax with scale and bias

Not for

    Tags

    • triton
    • gpu
    • pytorch
    • kernel

    About

    You say

    “Write a Triton kernel that computes a row-wise softmax with masking, then compare it with torch.softmax.”

    Card for the “Writing GPU kernels with Triton” skill

    Skill published by mohitmishra786 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 write Python GPU kernels with Triton and integrate them with PyTorch
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md7.1 KB

    Origin and licence

    Listed unmodified

    Author
    mohitmishra786
    Source
    github.com/mohitmishra786/low-level-dev-skills/tree/bdc58472fa9f309ed1b3f7d985a0d8e9bd8f4608/skills/gpu/triton-lang
    Licence
    MIT

    Notice

    « triton-lang » (mohitmishra786, 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.