Ryan Dick 4105a78b83 Update load_flux_model_bnb_llm_int8.py to work with a single-file FLUX transformer checkpoint.

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 InvokeInt8Params that was causing it to use double the necessary VRAM.

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

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

fast_quantized_diffusion_model.py

Move requantize.py to the quatnization/ dir.

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

fast_quantized_transformers_model.py

Move requantize.py to the quatnization/ dir.

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

load_flux_model_bnb_llm_int8.py

Update load_flux_model_bnb_llm_int8.py to work with a single-file FLUX transformer checkpoint.

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

load_flux_model_bnb_nf4.py

WIP on moving from diffusers to FLUX

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

requantize.py

Move requantize.py to the quatnization/ dir.

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