Ryan Dick dc54e8763b Add CustomInvokeLinearNF4 to enable CPU -> GPU streaming for InvokeLinearNF4 layers.

2024-12-24 14:32:11 +00:00

..

data

Get convert_flux_kohya_state_dict_to_invoke_format(...) working, with unit tests.

2024-09-15 04:39:56 +03:00

load/model_cache/torch_module_autocast

Add CustomInvokeLinearNF4 to enable CPU -> GPU streaming for InvokeLinearNF4 layers.

2024-12-24 14:32:11 +00:00

model_loading

tidy(mm): remove convenience methods from high level model manager service

2024-03-07 10:56:59 +11:00

model_metadata

Add unit test

2024-03-19 01:16:11 -04:00

util

Update HF download logic to work for black-forest-labs/FLUX.1-schnell.

2024-08-26 20:17:50 -04:00

model_manager_fixtures.py

Rename model_cache_default.py -> model_cache.py.

2024-12-24 14:23:18 +00:00

test_libc_util.py

Tidy names and locations of modules

2024-03-01 10:42:33 +11:00

test_memory_snapshot.py

final tidying before marking PR as ready for review

2024-03-01 10:42:33 +11:00

test_model_load_optimization.py

Tidy names and locations of modules

2024-03-01 10:42:33 +11:00