Skip to content
OutageDeck

Incident detail

Degraded scale-out due to failed setups pulling from huggingface

Resolved incidentMinor

Timeline window

to

Outage alerts

Get alerted the next time Replicate breaks

Free email alerts for up to 5 providers. No card, live in about a minute. Paid plans add Slack, Teams, Discord, and webhook delivery across your whole stack, plus higher API quotas.

Set up free alertsHow Replicate alerts work

Timeline

Incident updates

Every update Replicate posted, oldest to newest, exactly as it appeared on their official status page.

  1. Identified

    Models that pull from huggingface during setup have not been succeeding, which is resulting in scale-out delays and queue backups.

  2. Identified

    We have confirmed that turning off our caching layer for huggingface downloads allows models to successfully set up, so we are making that change for all models while we continue to troubleshoot.

  3. Monitoring

    All affected hardware types have recovered and we are continuing to monitor and troubleshoot. Thanks for your patience!

  4. Resolved

    We're looking stable now, and with caching back on. Thanks again for your patience!

Keep exploring

More from Replicate

Neighboring incidents on Replicate's timeline and the rest of their record on OutageDeck.

← Older incident

Hitting GPU Capacity for H100s creating large queue times for some models

All Replicate incidentsReplicate live status