InvokeAI

mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-02-01 09:05:18 -05:00

Files

Kent Keirsey 1f63b60021 Implementing support for Non-Standard LoRA Format (#7985 )

* integrate loRA

* idk anymore tbh

* enable fused matrix for quantized models

* integrate loRA

* idk anymore tbh

* enable fused matrix for quantized models

* ruff fix

---------

Co-authored-by: Sam <bhaskarmdutt@gmail.com>
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>

2025-05-05 09:40:38 -04:00

cached_model

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

torch_module_autocast

Implementing support for Non-Standard LoRA Format (#7985 )

2025-05-05 09:40:38 -04:00

__init__.py

Remove ModelCacheBase.

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

cache_record.py

First pass at adding partial loading support to the ModelCache.