Jeffrey Morgan c4cf8ad559
llm: avoid loading model if system memory is too small (#5637)
* llm: avoid loading model if system memory is too small

* update log

* Instrument swap free space

On linux and windows, expose how much swap space is available
so we can take that into consideration when scheduling models

* use `systemSwapFreeMemory` in check

---------

Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
2024-07-11 16:42:57 -07:00
..
2024-07-10 13:43:47 -07:00
2024-07-09 11:34:30 -07:00
2024-06-20 09:57:27 -07:00