DocShotgun a635a719d7 Model: Enable draft model q-cache in Exl3 ...

* Remove unneeded default fp16 cache layer import

2025-05-03 20:59:36 -07:00

..

exllamav2

Model: Initial Exl3 cache quantization support

2025-05-03 20:35:35 -07:00

exllamav3

Model: Enable draft model q-cache in Exl3

2025-05-03 20:59:36 -07:00

infinity

Model: Add proper jobs cleanup and fix var calls

2025-04-24 21:30:55 -04:00

base_model_container.py

Model: Add exl3 and associated load functions

2025-05-02 21:32:39 -04:00