Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging.
Install
npx skills add NVIDIA/skills --skill tilegym-improve-cutile-kernel-perfnpx skills add NVIDIA/skills --skill tilegym-improve-cutile-kernel-perf -a claude-code -gnpx skills add NVIDIA/skills --skill tilegym-improve-cutile-kernel-perf -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tilegym-improve-cutile-kernel-perfgh skill install NVIDIA/skills tilegym-improve-cutile-kernel-perfgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/tilegym-improve-cutile-kernel-perf ~/.claude/skills/tilegym-improve-cutile-kernel-perf # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tilegym-improve-cutile-kernel-perf ~/.agents/skills/tilegym-improve-cutile-kernel-perf # Codex, Cursor, Gemini CLI, Copilot, OpenCode