cuda-triton-multiarch

0.2.2

Triton GPU kernels for transformer operations — softmax, FlashAttention-2, RMSNorm, SwiGLU, quantized matmul

License

A short and simple permissive license with conditions only requiring preservation of copyright and license notices. Licensed works, modifications, and larger works may be distributed under different terms and without source code.

Published

June 26, 2026

7d ago

Package Registry

PyPI Source

README badge Customize →

License Sources Match

MIT confirmed by 2 independent sources — Python registry metadata and the LICENSE file in the package source — as of June 26, 2026.

Source	License	Class
Licensie (detected)	MIT	Permissive
PyPI (reported)	MIT	Permissive

Loading dependencies…

License File

Added Removed Expected

Versions

4 versions

Version	License	Published	Status
0.2.2 Latest Viewing	MIT	Jun 26, 2026	Scanned
0.2.1	MIT	Jun 25, 2026	Scanned
0.1.3	MIT	Jun 25, 2026	Scanned
0.1.0	MIT	Jun 25, 2026	Scanned