huggingface-zerogpu
skills/huggingface-zerogpu · huggingface/skills · by Hugging Face
AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints · pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures · even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.
Source · GitHub API and the SKILL.md frontmatter, read 2026-11-15 · stars are for the whole huggingface/skills repository
Install huggingface-zerogpu
Ready-to-paste · from the repository README and the skill folder
# Copy this skill folder into your personal Claude Code skills git clone --depth 1 --filter=blob:none --sparse --branch main https://github.com/huggingface/skills.git /tmp/huggingface-zerogpu-src git -C /tmp/huggingface-zerogpu-src sparse-checkout set skills/huggingface-zerogpu mkdir -p ~/.claude/skills cp -R /tmp/huggingface-zerogpu-src/skills/huggingface-zerogpu ~/.claude/skills/huggingface-zerogpu
Skill repositories from other publishers in the open Agent Skills format (agentskills.io) · a folder with a SKILL.md plus optional scripts and resources, read by any client that supports the format.
Alternatives
Same category · other repositories · latest commit first
More from Hugging Face
Same repository · huggingface/skills · latest commit first
Embeddable badge
Drop into your README · links to this skill page
[](https://benchgecko.ai/skills/huggingface-zerogpu)
FAQ
Built from the GitHub data above
What is huggingface-zerogpu?
huggingface-zerogpu is a Agent Skills agent skill by Hugging Face, in the skills/huggingface-zerogpu folder of the huggingface/skills repository (BenchGecko category: DevOps · IaC). Its SKILL.md describes it as: AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints · pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures · even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.
Where does this data come from?
From GitHub, read 2026-11-15: the name and description from the SKILL.md frontmatter, 5 files from the repository tree, the last commit to the folder on 2026-05-20, and 11,351 stars for the whole huggingface/skills repository. BenchGecko does not rate skills.
How do I install huggingface-zerogpu?
Copy the skills/huggingface-zerogpu folder into ~/.claude/skills/ for Claude Code, use the command from the huggingface/skills README, or point any client that supports the Agent Skills format at the folder. Ready-to-paste snippets are above.
Is huggingface-zerogpu official?
huggingface-zerogpu is published in huggingface/skills, a repository owned by the Hugging Face organization on GitHub.
See also
Keep exploring the BenchGecko graph