Degraded scale-out due to failed setups pulling from huggingface

Update timeline

1. identified Jul 31, 2026, 09:25 PM UTC

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

2. identified Jul 31, 2026, 09:26 PM UTC

   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 Jul 31, 2026, 10:27 PM UTC

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

4. resolved Jul 31, 2026, 11:39 PM UTC

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