# Hugging Face — Custom Kernels for All from Codex and Claude

- Company: Hugging Face (huggingface.co)
- Announced: 2026-02-13T00:00:00+00:00
- Category: developer-tool-release
- Subject: Platform
- Models affected: Qwen3-8B
- Source: https://huggingface.co/blog/custom-cuda-kernels-agent-skills
- Record: https://forck.live/items/1547-custom-kernels-for-all-from-codex-and-claude

Hugging Face releases an agent skill that enables coding agents (Claude, Codex) to write production CUDA kernels for transformers and diffusers, including PyTorch bindings and benchmarks.

## Evidence

Verbatim from https://huggingface.co/blog/custom-cuda-kernels-agent-skills:

> We built an agent skill that teaches coding agents how to write production CUDA kernels. Then we pointed Claude and Codex at two real targets: a diffusers pipeline and a transformers model. The agents produced working kernels for both, with correct PyTorch bindings and benchmarks, end to end.

---

Record: https://forck.live/items/1547-custom-kernels-for-all-from-codex-and-claude
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md