Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-18 16:54:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

Cleanup

Browse Source
This commit is contained in:
Disty0
2025-08-11 15:11:29 +03:00
parent afb3a5a06d
commit f45e3342e6
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/sdnq/__init__.py
+2
View File
@@ -412,6 +412,8 @@ class SDNQConfig(QuantizationConfigMixin):
Same as use_quantized_matmul_conv but for the convolutional layers with UNets like SDXL.
dequantize_fp32 (`bool`, *optional*, defaults to `False`):
Enabling this option will use FP32 on the dequantization step.
non_blocking (`bool`, *optional*, defaults to `False`):
Enabling this option will use non blocking ops when moving layers between the quantization device and the return device.
quantization_device (`torch.device`, *optional*, defaults to `None`):
Used to set which device will be used for the quantization calculation on model load.
return_device (`torch.device`, *optional*, defaults to `None`):