Index of every page on this site: llms.txt
All skills
nvidia avatar

/tilegym-monkey-patch-kernels-to-transformers

@81b3b24
by NVIDIA Corporationnvidia/tilegym847 stars
92
Run it yourself

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)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.

  • 10 files
  • 1.1 MB
  • CC-BY-4
  • Updated 6 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/nvidia/tilegym/tilegym-monkey-patch-kernels-to-transformers

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈93 tokens for metadata: the name and description. ≈551 when used: this file. ≈10k more on demand in 7 files.

Description uses 4.7% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈372 characters, or 4.7%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Integrate and create cuTile kernels into 🤗 Transformers

The main purpose of TileGym project is to provide performant kernels for LLM training and inference. We will integrate proper kernels available in TileGym project to LLM models provided by Hugging Face transformers library to validate end-to-end functional correctness and performance improvements. Instead of modifying transformers source code, we will take a non-intrusive monkey-patch approach: We will replace certain modules/classes/methods in transformers library that implement the Transformer model we would like to integrate, such that at model instantiation, that model's core components will be replaced by TileGym implementations. At runtime the model will actually invoke TileGym kernels under the hood. In addition, we will follow an auto-research-style agent harness loop to create and integrate new cuTile kernels to the target model to improve kernel coverage and end-to-end throughput.

Instructions

This is for human readers: Simply prompt your favorite AI Agent with skill name and target model ID. E.g.,:

Hi, please /monkey-patch-kernels-to-transformers Qwen/Qwen3.5-0.8B.

The Agent might ask you several questions. Make clarifications and give a go confirmation.

Workflow

  1. Prepare experiment environment. Follow environment-setup.md
  2. Integrate existing TileGym kernels to the target model. Follow kernel-integration.md
  3. Autonomously create new cuTile kernels for uncovered PyTorch code. Follow auto-kernelize.md
    • Feel free to add new cuTile kernels with constraints in mind
    • Do not stop until meet auto-kernelize loop stop conditions
  4. Summarize and report

Disciplines

This is for AI Agents executing this workflow.

Kernel inventory

Reusable transformer-local kernels must be represented with FlashInfer-Bench-style Definition and Solution metadata. Follow kernel-inventory-schema.md when researching compute requirements, inventorying existing kernels, proposing candidates, or creating new generated kernels.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 81b3b24. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 6 months ago
Other metadata
compatibility
Verified on Claude Code with Opus-4.6 and onward, CodeX with GPT-5.5 and onward, and Cursor (Agent mode) with GPT-5.3-CodeX and stronger models.
metadata
{
  "author": "TileGym Team <TileGym@nvidia.com>",
  "version": "2026.06.03",
  "tags": [
    "tilegym",
    "transformers",
    "integration",
    "kernel",
    "monkey-patch"
  ]
}

README badge

README badge for nvidia/tilegym/tilegym-monkey-patch-kernels-to-transformers