framework-internalsdevelopment
adding-cutile-kernel
Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to register a new cuTile op.
maintainer
NVIDIA
Updated 3/6/2026
Stars
699
Forks
60
quick start
Installation and usage
Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to register a new cuTile op.
Installation
$ install --globalskills.sh
Usage
Once installed, you can use this skill by running the following command in your terminal:
skills use adding-cutile-kernel