Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-20 01:31:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

SDNQ move non_blocking to quant config

Browse Source
This commit is contained in:
Disty0
2025-08-11 15:07:02 +03:00
parent dc7b25d387
commit afb3a5a06d
3 changed files with 14 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/model_quant.py
+2
View File
@@ -146,6 +146,7 @@ def create_sdnq_config(kwargs = None, allow: bool = True, module: str = 'Model',
use_quantized_matmul=shared.opts.sdnq_use_quantized_matmul,
use_quantized_matmul_conv=shared.opts.sdnq_use_quantized_matmul_conv,
dequantize_fp32=shared.opts.sdnq_dequantize_fp32,
non_blocking=shared.opts.diffusers_offload_nonblocking,
quantization_device=quantization_device,
return_device=return_device,
modules_to_not_convert=modules_to_not_convert,
@@ -418,6 +419,7 @@ def sdnq_quantize_model(model, op=None, sd_model=None, do_gc: bool = True, weigh
use_quantized_matmul=shared.opts.sdnq_use_quantized_matmul,
use_quantized_matmul_conv=shared.opts.sdnq_use_quantized_matmul_conv,
dequantize_fp32=shared.opts.sdnq_dequantize_fp32,
non_blocking=shared.opts.diffusers_offload_nonblocking,
quantization_device=quantization_device,
return_device=return_device,
param_name=op,