Lincoln Stein d32f9f7cb0 reverse logic of gpu_mem_reserved ...

- gpu_mem_reserved now indicates the amount of VRAM that will be reserved
  for model caching (similar to max_cache_size).

2023-07-11 15:16:40 -04:00

..

models

merge with main, fix conflicts

2023-07-06 15:21:45 -04:00

__init__.py

model merging API ready for testing

2023-07-06 13:15:15 -04:00

convert_ckpt_to_diffusers.py

Fix ckpt scanning on conversion

2023-07-05 14:18:30 +03:00

lora.py

Merge branch 'main' into feat/clip_skip

2023-07-07 16:21:53 +12:00

model_cache.py

reverse logic of gpu_mem_reserved

2023-07-11 15:16:40 -04:00

model_manager.py

reverse logic of gpu_mem_reserved

2023-07-11 15:16:40 -04:00

model_merge.py

add merge api

2023-07-06 15:12:34 -04:00

model_probe.py

improve user migration experience

2023-07-07 08:18:46 -04:00