mirror of
https://github.com/ollama/ollama.git
synced 2025-09-07 01:00:54 +02:00
The current scheduler algorithm of picking the paralellism based on available VRAM complicates the upcoming dynamic layer memory allocation algorithm. This changes the default to 1, with the intent going forward that parallelism is explicit and will no longer be dynamically determined. Removal of the dynamic logic will come in a follow up.