Generated banner for Tilegym Improve Cutile Kernel Perf
Generated logo for Tilegym Improve Cutile Kernel Perf

Tilegym Improve Cutile Kernel Perf

NVIDIAOfficialCreated by TileGym TeamDistributed by NVIDIA

  • Skill
  • Workflow
  • Software development
  • Link-only
  • Medium risk

From the author

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. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
— the description by TileGym Team

Install

Documentation by TileGym Team

The licence of this skill does not allow us to copy its documentation. Read it at the source

Files

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python, Needs Node.js

Security

What our scanner noticed· Medium risk

  • Large base64-encoded blobs
  • Instructions that use the network

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
TileGym Team
Publisher
NVIDIA (Official)
Distributed by
NVIDIA
Source
NVIDIA/skills · skills/tilegym-improve-cutile-kernel-perf · commit fce3cca
Licence
Unrecognised licence declaration: CC-BY-4.0 AND Apache-2.0 (link-only: we do not redistribute its files)
Synced

AutoGineer is not affiliated with or endorsed by TileGym Team or NVIDIA.

Get it from the source

This skill’s licence does not allow redistribution, so we link to it instead: NVIDIA/skills