Stars
★ 2.8k
Use when adding, modifying, optimizing, or debugging CuTile autotuning code.
Install this skill (Claude Code)
# Clone and copy the skill into your project
git clone https://github.com/NVIDIA/skills.git
mkdir -p .claude/skills
cp -r skills/skills/TileGym/cutile-autotuning .claude/skills/
# Or for personal use: ~/.claude/skills/Add a new cuTile GPU kernel operator to TileGym.
Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents.
Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit).
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning.
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' in...