·cuda-kernels
*

cuda-kernels

huggingface/kernels

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations.

6Installs·1Trend·@huggingface

Installation

$npx skills add https://github.com/huggingface/kernels --skill cuda-kernels

SKILL.md

This skill provides patterns and guidance for developing optimized CUDA kernels targeting NVIDIA GPUs (H100, A100, T4) for use with HuggingFace diffusers and transformers libraries.

Load pre-compiled kernels from HuggingFace Hub (no local compilation):

| diffusers | LTX-Video, Stable Diffusion, FLUX, DiT | RMSNorm, GEGLU, RoPE, AdaLN | | transformers | LLaMA, Mistral, Qwen, Falcon | RMSNorm, Attention |

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations. Source: huggingface/kernels.

View raw

Facts (cite-ready)

Stable fields and commands for AI/search citations.

Install command
npx skills add https://github.com/huggingface/kernels --skill cuda-kernels
Category
*Creative Media
Verified
First Seen
2026-02-17
Updated
2026-02-18

Quick answers

What is cuda-kernels?

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations. Source: huggingface/kernels.

How do I install cuda-kernels?

Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/huggingface/kernels --skill cuda-kernels Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor

Where is the source repository?

https://github.com/huggingface/kernels

Details

Category
*Creative Media
Source
skills.sh
First Seen
2026-02-17

Related Skills

None