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.
Installation
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.
Facts (cite-ready)
Stable fields and commands for AI/search citations.
- Install command
npx skills add https://github.com/huggingface/kernels --skill cuda-kernels- Source
- huggingface/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