reduce VRAM usage, instead of increasing main RAM usage

This commit is contained in:
Kohya S
2024-10-27 10:19:05 +09:00
parent 56b4ea963e
commit ca44e3e447
2 changed files with 14 additions and 4 deletions

View File

@@ -137,6 +137,13 @@ The majority of scripts is licensed under ASL 2.0 (including codes from Diffuser
## Change History
### Oct 27, 2024 / 2024-10-27:
- `svd_merge_lora.py` VRAM usage has been reduced. However, main memory usage will increase (32GB is sufficient).
- This will be included in the next release.
- `svd_merge_lora.py` のVRAM使用量を削減しました。ただし、メインメモリの使用量は増加します32GBあれば十分です
- これは次回リリースに含まれます。
### Oct 26, 2024 / 2024-10-26:
- Fixed a bug in `svd_merge_lora.py`, `sdxl_merge_lora.py`, and `resize_lora.py` where the hash value of LoRA metadata was not correctly calculated when the `save_precision` was different from the `precision` used in the calculation. See issue [#1722](https://github.com/kohya-ss/sd-scripts/pull/1722) for details. Thanks to JujoHotaru for raising the issue.