mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-22 14:53:56 +00:00
If we get our predictions wrong, this can be used to set a lower memory limit as a workaround. Recent multi-gpu refactoring accidentally removed it, so this adds it back.
5.3 KiB
5.3 KiB