🚀 Get started with your gradio Space!

Your new space has been created, follow these steps to get started (or read the full documentation)

Start by cloning this repo by using:

Use an access token as git password/credential

# When prompted for a password, use an access token with write permissions.

# Generate one from your settings: https://huggingface.co/settings/tokens

git clone https://huggingface.co/spaces/cbensimon/zerogpu-quickstart

Create your gradio app.py file:

import gradio as gr
import spaces
import torch

zero = torch.Tensor([0]).cuda()
print(zero.device) # <-- 'cpu' 🤔

@spaces.GPU
def greet(n):
    print(zero.device) # <-- 'cuda:0' 🤗
    return f"Hello {zero + n} Tensor"

demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
demo.launch()

Then commit and push:

						$git add app.py
						$git commit -m "Add application file"
						$git push

Hint Alternatively, you can create the app.py file directly in your browser.

Finally, your Space should be running on this page after a few moments!

Dependencies

You can add a requirements.txt file at the root of the repository to specify Python dependencies

If needed, you can also add a packages.txt file at the root of the repository to specify Debian dependencies.

The gradio package is pre-installed and its version is set in the sdk_version field in the README.md file.

Personalize your Space

Make your Space stand out by customizing its emoji, colors, and description by editing metadata in its README.md file.

Documentation

Read the full documentation for gradio Spaces here.