Oom-killer kills process often after update

Shows how to run Flux schnell under 17GBs without bells and whistles. It additionally shows how to serialize the quantized checkpoint and load it back.

Summary

Shows how to run Flux schnell under 17GBs without bells and whistles. It additionally shows how to serialize the quantized checkpoint and load it back. · GitHub

Report Flux Performance Problems (TLDR: DO NOT set “GPU Weight” too high! Lower “GPU Weight” solves 99% problems!)