|
|
70def37280
|
Move quantization scripts to a scripts/ subdir.
|
2024-08-23 18:08:37 +00:00 |
|
|
|
8af3c72de7
|
Update docs for T5 quantization script.
|
2024-08-23 18:07:14 +00:00 |
|
|
|
6405214940
|
Remove all references to optimum-quanto and downgrade diffusers.
|
2024-08-23 18:04:17 +00:00 |
|
|
|
86e49c423c
|
Fixes to the T5XXL quantization script.
|
2024-08-23 18:03:23 +00:00 |
|
|
|
6d838fa997
|
Add script for quantizing a T5 model.
|
2024-08-23 18:03:23 +00:00 |
|
|
|
42bbab74b3
|
Add docs to the quantization scripts.
|
2024-08-21 19:08:28 +00:00 |
|
|
|
203542c7a8
|
Update load_flux_model_bnb_llm_int8.py to work with a single-file FLUX transformer checkpoint.
|
2024-08-21 19:08:16 +00:00 |
|
|
|
7f62033f1f
|
Fix bug in InvokeInt8Params that was causing it to use double the necessary VRAM.
|
2024-08-21 19:08:00 +00:00 |
|
|
|
e41025ddc7
|
Move requantize.py to the quatnization/ dir.
|
2024-08-21 18:21:44 +00:00 |
|
|
|
d11dc6ddd0
|
Remove duplicate log_time(...) function.
|
2024-08-21 18:10:24 +00:00 |
|
|
|
dd24f83d43
|
Fix styling/lint
|
2024-08-21 09:10:22 -04:00 |
|
|
|
115f350f6f
|
Install sub directories with folders correctly, ensure consistent dtype of tensors in flux pipeline and vae
|
2024-08-21 09:09:39 -04:00 |
|
|
|
46b6314482
|
Run Ruff
|
2024-08-21 09:06:38 -04:00 |
|
|
|
46d5107ff1
|
Run Ruff
|
2024-08-21 09:06:38 -04:00 |
|
|
|
6ea1278d22
|
Manage quantization of models within the loader
|
2024-08-21 09:06:34 -04:00 |
|
|
|
d7a39a4d67
|
WIP on moving from diffusers to FLUX
|
2024-08-21 08:59:19 -04:00 |
|
|
|
3e8a550fab
|
More improvements for LLM.int8() - not fully tested.
|
2024-08-21 08:59:19 -04:00 |
|
|
|
0e96794c6e
|
LLM.int8() quantization is working, but still some rough edges to solve.
|
2024-08-21 08:59:19 -04:00 |
|
|
|
23a7328a66
|
Clean up NF4 implementation.
|
2024-08-21 08:59:19 -04:00 |
|
|
|
cdd47b657b
|
Make quantized loading fast for both T5XXL and FLUX transformer.
|
2024-08-21 08:59:19 -04:00 |
|
