Files
mlx/tests/metal_tests.cpp
Ethan a749a91c75 Support disable metal buffer cache to prevent performance degradation caused by large memory caching (#390)
* support disable metal buffer cache, due to large unused memory buffered when llm generated long context tokens

* Run format and add "cache_enabled" feature tests
2024-01-18 08:33:34 -08:00

14 KiB