apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 00:57:33 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix w8a8.py (#3733)

Browse Source
This commit is contained in:
co63oc
2025-09-03 10:57:26 +08:00
committed by GitHub
parent f7a4bea785
commit ce998449e0
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/model_executor/layers/quantization/w8a8.py
View File

@@ -85,7 +85,7 @@ class W8A8LinearMethod(QuantMethodBase):
if weight_scale is None or in_scale is None: if weight_scale is None or in_scale is None:
self.skip_quant = True self.skip_quant = True
return return
layer.wieght = layer.create_parameter( layer.weight = layer.create_parameter(
shape=layer.weight_shape, shape=layer.weight_shape,
dtype=layer.weight_dtype, dtype=layer.weight_dtype,
is_bias=False, is_bias=False,