huggingface avatar

Huggingface Zerogpu

This teaches Claude how to write and debug Gradio apps that run on Hugging Face's ZeroGPU infrastructure, where you get fractional GPU slices on demand instead of a dedicated card. It covers the decorator syntax (@spaces.GPU), the quirky process isolation model (models load at module scope but inference runs in forked workers), duration tuning (default 60s blocks users even if your task takes 10s), and all the sharp edges like no torch.compile support and CUDA wheel-only dependencies. The bundled references explain why returning CUDA tensors hangs and how quota pre-checks work. If you're deploying ML demos on Spaces and hitting PicklingError or quota exceeded messages, this is the missing manual.

skills.sh installs
1.4K
GitHub stars
11.3K
last updated
Aug 21, 2026

Install

$ npx -y skills add huggingface/skills --skill huggingface-zerogpu --agent claude-code

Installs into .claude/skills of the current project.

Files

Hugging Face ZeroGPU

Rules and patterns for ML demos on Hugging Face Spaces with ZeroGPU hardware. Covers @spaces.GPU, duration and quota tuning, process isolation, the CUDA availability model, concurrency safety, and CUDA build constraints.

Scope

This skill is for Gradio SDK Spaces using ZeroGPU hardware. Docker and Static Spaces cannot schedule onto ZeroGPU, and Streamlit apps now run as Docker Spaces — so this skill applies only to Gradio. For general Gradio coding (components, layouts, event listeners), see the huggingface-gradio skill in this repo. The authoritative ZeroGPU docs live at https://huggingface.co/docs/hub/spaces-zerogpu — refer to them for the current backing GPU, runtime version lists, and tier thresholds, all of which change over time.

Reference Files

Sponsors

Details

Repository
github.com/huggingface/skills
Categories
Backend & APIs, DevOps & CI/CD, Documentation, Data Science & ML, Release Management, Python
First seen
Jul 14, 2026

More from huggingface/skills

All 24
1twillai avatartwill-cloud-coding-agenttwillai/skillsUse Twill Cloud Coding Agent to manage Twill's public v1 API workflows. Create/list/update tasks, stream and cancel jobs, manage scheduled tasks, list repositor1.4Kskills.sh installs
2browser-use avatarx402browser-use/browser-useSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up fron1.4Kskills.sh installs
3charleswiltgen avataraxiom-datacharleswiltgen/axiomUse when working with ANY data persistence, database, storage, CloudKit, migration, or serialization. Covers SwiftData, Core Data, GRDB, SQLite, CloudKit sync, 1.4Kskills.sh installs
4nvidia avatarcuopt-user-rulesnvidia/skillsBase rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.1.4Kskills.sh installs
5badlogic avatarbrave-searchbadlogic/pi-skillsWeb search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.1.4Kskills.sh installs
6bighardperson avatarneodata-financial-searchbighardperson/computer-science-skills-collectionNeoData Financial Search — 自然语言通用金融数据搜索服务。用自然语言查询股票、基金、指数、板块、 宏观经济、外汇、大宗商品等全品类金融数据,涵盖行情报价、财务报表(财报)、资金流向、研报评级、 事件公告等,支持结构化API数据和财经文章两种召回模式,即问即答。 Use when the use1.3Kskills.sh installs