Hugging Face releases gradio.Server for custom frontends
hugging face released gradio.server, allowing developers to pair custom frontends like react or vanilla js with gradio's backend infrastructure. the solution extends fastapi to provide ml-specific features including automatic queuing, concurrency control, and zerogpu support on spaces. a ~50-line python implementation manages the backend, while the gradio js client handles request queuing from the frontend.
Hugging Face introduced gradio.Server, a tool that decouples Gradio's backend infrastructure from its standard UI components. Built on FastAPI, gradio.Server allows developers to define custom API routes using @app.api() that inherit Gradio's queuing engine and concurrency management. This architecture supports complex frontends—such as the 1,300-line vanilla JS application demonstrated in the announcement—while utilizing backend features like ZeroGPU allocation and gradio_client compatibility.