Skip to content
AI Radar by Wagner Solution
CS
Menu
worth noting Tools and apps

Maintenance of Inference Endpoints may limit the creation of new H200 instances

clearly official source

Hugging Face announced ongoing maintenance of the H200 infrastructure for the Inference Endpoints service, with completion expected around 12:30 UTC. The creation of new H200 instances may be temporarily limited.

According to an announcement from Hugging Face, maintenance is currently underway on the H200 infrastructure for the Inference Endpoints service. The company expects completion at approximately 12:30 UTC.

The creation of new H200 instances may be temporarily limited during maintenance. The announcement therefore describes a possible limitation, rather than a confirmed complete halt to their creation.

What changed

Why it matters

When planning a deployment that requires a new H200 instance, allow for a possible wait for the instance to be created. The expected end of maintenance does not guarantee that availability will be restored at that exact time.

Relevant practical impact

What this means

01

For a business

Business deployments that depend on creating new H200 instances may face delays during maintenance.

Development
What to decide Before a deployment that requires a new H200 instance, check the current maintenance status of the Inference Endpoints service.
More business impacts →
H200 Hugging Face Inference Endpoints

Check the original

Event sources

clearly official source · 1 publisher, 0 independent. We count feeds from the same owner only once.

1
Hugging Face Status — incident history official service status · first detected Maintenance: Scheduled maintenance: Inference Endpoints (H200)