cuda>=12.8

[signal idol]

I have this on half of my serverless endpoint I run , it just infinite load and take credits until I kill it :

2026-04-12T21:22:04Z start container for runpod/flash:latest: begin
2026-04-12T21:22:05Z error starting container: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running prestart hook #0: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy'
nvidia-container-cli: requirement error: unsatisfied condition: cuda>=12.8, please update your driver to a newer version, or use an earlier cuda container: unknown

And it does this message every 3 seconds and eat my credits and money. Can you please update all "host" to allow >=12.8 and not only half of them ?

[dire tapir]

To help others find answers, you can mark your question as solved via Right click solution message -> Apps -> ✅ Mark Solution