InvokeAI/invokeai/backend/quantization
2024-08-29 19:08:18 +00:00
..
scripts Rename params for flux and flux vae, add comments explaining use of the config_path in model config 2024-08-26 20:17:50 -04:00
__init__.py Move requantize.py to the quatnization/ dir. 2024-08-26 20:17:50 -04:00
bnb_llm_int8.py Fix bug in InvokeLinear8bitLt that was causing old state information to persist after loading from a state dict. This manifested as state tensors being left on the GPU even when a model had been offloaded to the CPU cache. 2024-08-29 19:08:18 +00:00
bnb_nf4.py Install sub directories with folders correctly, ensure consistent dtype of tensors in flux pipeline and vae 2024-08-26 20:17:50 -04:00