Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-08-25 · high
Each output in the graph gets its own REST endpoint on deploy, callable from gradio_client or curl.
Why now: The feature is new enough that Hugging Face's own guide is still the only walkthrough.
Gradio added gr.Workflow, a way to describe a process as a graph of typed nodes. Push it to Hugging Face Spaces and it builds both a UI and a REST endpoint for every output node, per Hugging Face's guide. That collapses a step teams usually do by hand. They build an interactive demo, then write a separate API layer so other services can call the same logic.
You can chain nodes in sequence or fan one input out to run several in parallel. Nodes can be Hugging Face Inference Providers, existing Spaces, or plain Python functions, mixed in the same graph.
The minimal setup is gr.Workflow(bind=[your_function]).launch(). GPU nodes use the @spaces.GPU decorator with ZeroGPU, so a node can grab GPU time without managing the allocation yourself.
The guide doesn't say what happens when one node in a parallel fan-out times out, or how an error in one branch affects the others. For a single function or a two-node chain that gap doesn't matter. For a dozen nodes mixing GPU calls and external Providers, it's the first thing to test before trusting it in production.
Each link below shares sources, entities, or timing with this story.
Hugging Face released Skills / Shared entities / Earlier coverage
Linked by a graph relationship (Hugging Face released Skills); both cover Hugging Face, Minimal; earlier Hugging Face coverage from 2026-05-20.
Hugging Face criticizes OpenAI / Shared entity: Hugging Face / Same source domain / Earlier coverage
Linked by a graph relationship (Hugging Face criticizes OpenAI); both cover Hugging Face; reported by the same outlet (huggingface.co).
Hugging Face criticizes OpenAI / Shared entity: Hugging Face / Earlier coverage / Tension
Linked by a graph relationship (Hugging Face criticizes OpenAI); both cover Hugging Face; earlier Hugging Face coverage from 2026-07-23.
Hugging Face criticizes OpenAI / Shared entity: GPU / Earlier coverage / Tension
Linked by a graph relationship (Hugging Face criticizes OpenAI); both cover GPU; earlier GPU coverage from 2026-04-30.
Claude Code uses Hugging Face / Shared entities / Same source domain / Earlier coverage
Linked by a graph relationship (Claude Code uses Hugging Face); both cover Hugging Face, Spaces; reported by the same outlet (huggingface.co).
Hugging Face criticizes OpenAI / Shared entity: GPU / Earlier coverage
Linked by a graph relationship (Hugging Face criticizes OpenAI); both cover GPU; earlier GPU coverage from 2026-08-08.
Linked by a graph relationship (Hugging Face criticizes OpenAI); both cover GPU; earlier GPU coverage from 2026-08-05.
Hugging Face criticizes OpenAI / Shared entity: Python / Earlier coverage
Linked by a graph relationship (Hugging Face criticizes OpenAI); both cover Python; earlier Python coverage from 2026-07-31.