VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-17 17:24:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

doc: add dtype comment for load_safetensors_with_lora_and_fp8 function

Browse Source
This commit is contained in:
Kohya S
2026-02-23 15:24:56 +09:00
parent 2c2e2e02d7
commit 5978694223
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
library/lora_utils.py
View File

@@ -65,6 +65,7 @@ def load_safetensors_with_lora_and_fp8(
fp8_optimization (bool): Whether to apply FP8 optimization.
calc_device (torch.device): Device to calculate on.
move_to_device (bool): Whether to move tensors to the calculation device after loading.
dit_weight_dtype (Optional[torch.dtype]): Dtype to load weights in when not using FP8 optimization.
target_keys (Optional[List[str]]): Keys to target for optimization.
exclude_keys (Optional[List[str]]): Keys to exclude from optimization.
disable_numpy_memmap (bool): Whether to disable numpy memmap when loading safetensors.