README.md

---
title: README
emoji: 🌍
colorFrom: indigo
colorTo: indigo
sdk: static
pinned: false
---
<div style="height: 15px;"></div>

# ZeroGPU Spaces

<div class="not-prose bg-gradient-to-r from-gray-50-to-white text-gray-900 border" style="border-radius: 8px; padding: 0.5rem 1rem;">
  <span style="font-weight: 600;">ZeroGPU is currently in beta:</span> 
  <ul class="list-disc list-inside pl-8">
    <li>It's available for everyone to use: <a class="underline" target="_blank" href="https://huggingface.co/spaces/enzostvs/zero-gpu-spaces">Browse dedicated Spaces list</a>.</li>
    <li><a target="_blank" href="https://huggingface.co/subscribe/pro" class="underline">PRO</a> users or <a target="_blank" class="underline" href="https://huggingface.co/enterprise" style="color: inherit;">Enterprise</a> organizations can <a href="https://huggingface.co/new-space?sdk=gradio" target="_blank" class="underline">host their own ZeroGPU Spaces<a/> under their namespaces. </li>
  </ul>
</div>

<div class="not-prose bg-gradient-to-r from-gray-50-to-white text-gray-900 border" style="border-radius: 8px; padding: 0.5rem 1rem; margin-top: 10px;">
  <span style="font-weight: 600;">Please share your feedback about ZeroGPU</span> in the <a class="underline" target="_blank" href="https://huggingface.co/spaces/zero-gpu-explorers/README/discussions" style="color: inherit;">Community tab</a>.
</div>

<div class="not-prose bg-gradient-to-r from-gray-50-to-white text-gray-900 border" style="border-radius: 8px; padding: 0.5rem 1rem; margin-top: 10px;">
  <span style="font-weight: 600;">ZeroGPU works great with Dev Mode.</span> Learn more about <a target="_blank" href="https://huggingface.co/spaces/dev-mode-explorers/README" class="underline">Dev Mode</a>.
</div>

<img src="https://cdn-uploads.huggingface.co/production/uploads/5f17f0a0925b9863e28ad517/cAlvAOu9QC547zrmRVpS5.gif" style="width: 100%; max-width:950px"/>


*ZeroGPU* is a new kind of hardware for Spaces.

It has two goals :
- Provide **free GPU access** for Spaces
- Allow Spaces to run on **multiple GPUs**

This is achieved by making Spaces efficiently hold and release GPUs as needed
(as opposed to a classical GPU Space that holds exactly one GPU at any point in time)

ZeroGPU uses _Nvidia A100_ GPU devices under the hood (40GB of vRAM are available for each workloads)

<img src="https://cdn-uploads.huggingface.co/production/uploads/5f17f0a0925b9863e28ad517/naVZI-v41zNxmGlhEhGDJ.gif" style="width: 100%; max-width:550px"/>


## Compatibility

*ZeroGPU* Spaces should mostly be compatible with any PyTorch-based GPU Space.<br>
Compatibility with high level HF libraries like `transformers` or `diffusers` is slightly more guaranteed<br>
That said, ZeroGPU Spaces are not as broadly compatible as classical GPU Spaces and you might still encounter unexpected bugs

Also, for now, ZeroGPU Spaces only works with the **Gradio SDK**

Supported versions:
- Gradio: 4+
- PyTorch: All versions from `2.0.0` to `2.2.0` and `2.4.x` (2.3.x is not supported due to a PyToch [bug](https://github.com/pytorch/pytorch/issues/122085))
- Python: `3.10.13`

## Usage

In order to make your Space work with ZeroGPU you need to **decorate** the Python functions that actually require a GPU with `@spaces.GPU`<br>
During the time when a decorated function is invoked, the Space will be attributed a GPU, and it will release it upon completion of the function.<br>
Here is a practical example :

```diff
+import spaces
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(...)
pipe.to('cuda')

[email protected]
def generate(prompt):
    return pipe(prompt).images

gr.Interface(
    fn=generate,
    inputs=gr.Text(),
    outputs=gr.Gallery(),
).launch()
```

1. We first `import spaces` (importing it first might prevent some issues but is not mandatory)
2. Then we decorate the `generate` function by adding a `@spaces.GPU` line before its definition

Note that `@spaces.GPU` is effect-free and can be safely used on non-ZeroGPU environments

## Duration

If you expect your GPU function to take more than __60s__ then you need to specify a `duration` param in the decorator like:

```python
@spaces.GPU(duration=120)
def generate(prompt):
   return pipe(prompt).images
```

It will set the maximum duration of your function call to 120s.  
You can also specify a duration if you know that your function will take far less than the 60s default.  
The lower the duration, the higher priority your Space visitors will have in the queue

## Getting Started

To **explore and use existing ZeroGPU Spaces**, browse the following list: https://huggingface.co/spaces/enzostvs/zero-gpu-spaces

To **create and host your own ZeroGPU Spaces**:

  - For personal accounts:
    - <a href="https://huggingface.co/settings/billing/subscription" target="_blank">Subscribe to PRO</a>. Once subscribed, ZeroGPU will appear in the hardware list on <a href="https://huggingface.co/new-space" target="_blank">New Space page</a> when you select the Gradio SDK.
  - For organizations:
    - <a href="https://huggingface.co/enterprise" target="_blank">Subscribe to the Enterprise Hub</a>. This will enable you to host and collaborate on ZeroGPU Spaces with all your organization members.


## Limitations

**Personal accounts** (PRO subscribers) can host up to 10 ZeroGPU Spaces.

**Organization accounts** subscribed to the Enterprise Hub can host up to 50 ZeroGPU Spaces.


<div style="height: 35px;"></div>
<style>
  :root {
    --bg-color-light: rgba(255, 255, 255, 0.3);
    --bg-color-dark: rgba(0, 0, 0, 0.3);
    --text-color-light: rgb(0, 0, 0);
    --text-color-dark: rgb(255, 255, 255);
  }

  .theme-light {
    --bg-color: var(--bg-color-light);
    --text-color: var(--text-color-light);
  }

  .theme-dark {
    --bg-color: var(--bg-color-dark);
    --text-color: var(--text-color-dark);
  }

  .notice {
    background-color: var(--bg-color);
    color: var(--text-color);
    border-radius: 8px;
    padding: 0.5rem 1rem;
    margin-top: 10px;
  }

  .notice span {
    font-weight: 600;
  }
</style>