xtrah200 reboot at 14:45: GPU0 failure

Sent: 2026-08-11 · Type: maintenance

[Notice]

Hi all, unfortunately GPU0 on xtrah200 has failed, and a reboot is required to recover the node. We've scheduled it for 14:45 today.

Sorry for the short notice and please stop your jobs. If you have anything running that can't be interrupted, just let me know and we'll work around it.

Thanks for your understanding!