Hugging Face reported a temporary AWS CDN outage in the Singapore region
Hugging Face recorded 500 errors when downloading files from the CDN in the ap-southeast-1 region (Singapore) during two brief periods starting at 15:14 UTC. The service is running normally, but the underlying cause has not been fully resolved.
According to its status notice, Hugging Face recorded an increased error rate on AWS CDN in the Singapore region (ap-southeast-1). Some file downloads failed with HTTP 500 errors during two brief periods starting at 15:14 UTC.
The company stated that downloads are now working normally, but the underlying cause has not been fully resolved. According to Hugging Face, brief outages may therefore recur until a definitive fix is deployed. Other CDN regions were not affected by the incident.
Why it matters
Users and systems downloading models or datasets from Hugging Face through the ap-southeast-1 region may encounter brief download failures in the form of 500 errors until the company permanently resolves the issue. Automated pipelines (CI/CD, model deployment) in this region should account for the possibility of having to retry a request.
Two audiences, two different impacts
What this means
For individuals
If you download models or datasets from Hugging Face through the Singapore region, download errors (HTTP 500) may recur briefly until the underlying cause is resolved.
For a business
Companies running automated downloads from Hugging Face CDN in the ap-southeast-1 region (e.g. CI/CD or deployment pipelines) should expect brief outages until a permanent fix is in place and consider implementing request retries.
DevelopmentCheck the original
Event sources
clearly official source · 1 publisher, 0 independent. We count feeds from the same owner only once.