Plain-AyI
← All projects
Developer building blocks

CUTLASS

NVIDIA building blocks for fast matrix maths on graphics cards.

New this week

What it does

CUTLASS is a collection of reusable software parts from NVIDIA for doing high-performance matrix multiplication and related maths on NVIDIA graphics cards.

These operations are at the heart of deep learning, so the library is used as a building block inside custom high-speed programs and AI systems.

It also now includes Python interfaces, which its makers say make writing fast graphics-card code easier to learn.

Who it's for

Performance engineers and researchers writing fast code for NVIDIA graphics cards.

Can I use it without coding?

Developers only. It is a low-level programming library for C++ and Python developers. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Linux, Windows
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • No standard license listed. Check the GitHub page before using it for business.
  • More on staying safe

Where people are talking about it