mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-21 22:33:56 +00:00
When the same model is being reloaded rapidly with client connections being canceled before the model finishes loading, the queued unload event could cause a leak of runners by deleting a different runner from the loaded list.
32 KiB
32 KiB