CUTLASS Files

CUDA Templates for Linear Algebra Subroutines

This is an exact mirror of the CUTLASS project, hosted at https://github.com/NVIDIA/cutlass. SourceForge is not affiliated with CUTLASS.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	InfoDownloads / Week
v4.5.0	< 9 hours ago	0
v4.4.2	2026-03-17	2
v4.4.1	2026-02-27	0
v4.4.0	2026-02-26	0
v4.3.5	2026-01-08	0
Totals: 5 Items		2

Other Useful Business Software

Enterprise-grade ITSM, for every business

Give your IT, operations, and business teams the ability to deliver exceptional services—without the complexity.

Freshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.

Try it Free

$300 in Free Credit Towards Top Cloud Services

Build VMs, containers, AI, databases, storage—all in one place.

Start your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.

Get Started

$300 in Free Credit Towards Top Cloud Services

Build VMs, containers, AI, databases, storage—all in one place.

Start your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.

Get Started

Recommended Projects

Crown and Cutlass
Crown and Cutlass is a 3d pirate action/adventure game in the spirit of the old Pirates! game. It is written in C++, using OpenGL and SDL with an emphasis on cross-platform compatibility.
DeepGEMM
Clean and efficient FP8 GEMM kernels with fine-grained scaling
MNN
MNN is a blazing fast, lightweight deep learning framework
fftw++
FFTW++ is a C++ header class for the FFTW Fast Fourier Transform library that automates memory allocation, alignment, planning, wisdom, and communication on both serial and parallel (OpenMP/MPI) architectures. In 2D and 3D, hybrid dealiasing of convolutions substantially reduces memory usage and computation time. Wrappers for C, Python, and Fortran are included.
Spire
Powerful new number types and numeric abstractions for Scala

CUTLASS Files

CUDA Templates for Linear Algebra Subroutines

Get an email when there's a new version of CUTLASS