Commit Graph

14 Commits

Author SHA1 Message Date
David Burnett
6c0bd7d150 fix import ordering, remove code I reverted that the resync added back 2025-05-19 11:16:23 +10:00
David Burnett
8abcc99ced add check for state_dict, required to load TI's 2025-05-19 11:16:23 +10:00
David Burnett
73ab4b8895 fix offload device 2025-05-19 11:16:23 +10:00
David Burnett
86719f2065 revert to overload due to failing tests, use Torch futures instead 2025-05-19 11:16:23 +10:00
Ryan Dick
da589b3f1f Memory optimization to load state dicts one module at a time in CachedModelWithPartialLoad when we are not storing a CPU copy of the state dict (i.e. when keep_ram_copy_of_weights=False). 2025-01-16 17:00:33 +00:00
Ryan Dick
c76d08d1fd Add keep_ram_copy option to CachedModelOnlyFullLoad. 2025-01-16 15:08:23 +00:00
Ryan Dick
04087c38ce Add keep_ram_copy option to CachedModelWithPartialLoad. 2025-01-16 14:51:44 +00:00
Ryan Dick
d7ab464176 Offload the current model when locking if it is already partially loaded and we have insufficient VRAM. 2025-01-07 02:53:44 +00:00
Ryan Dick
1b7bb70bde Improve handling of cases when application code modifies the size of a model after registering it with the model cache. 2025-01-07 00:31:00 +00:00
Ryan Dick
7127040c3a Remove unused function set_nested_attr(...). 2025-01-07 00:31:00 +00:00
Ryan Dick
6d49ee839c Switch the LayerPatcher to use 'custom modules' to manage layer patching. 2024-12-29 01:18:30 +00:00
Ryan Dick
f8ab414f99 Add CachedModelOnlyFullLoad to mirror the CachedModelWithPartialLoad for models that cannot or should not be partially loaded. 2024-12-24 14:32:11 +00:00
Ryan Dick
c6795a1b47 Make CachedModelWithPartialLoad work with models that have non-persistent buffers. 2024-12-24 14:32:11 +00:00
Ryan Dick
0a8fc74ae9 Add CachedModelWithPartialLoad to manage partially-loaded models using the new autocast modules. 2024-12-24 14:32:11 +00:00