apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[NewFeatures] support eplb (#3547)

Browse Source 
* [NewFeatures] support eplb

* fix eplb
This commit is contained in:
xiaoxiaohehe001
2025-08-26 16:19:30 +08:00
committed by GitHub
parent 56e2d7e668
commit 9afa236e39
17 changed files with 174 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/model_executor/layers/backends/gcu/quantization/weight_only.py
View File

@@ -59,7 +59,7 @@ class GCUWeightOnlyLinearMethod(WeightOnlyLinearMethod):
is_bias=False,
)
def process_prequanted_weights(self, layer, state_dict) -> None:
def process_prequanted_weights(self, layer, state_dict, is_rearrange: bool = False) -> None:
"""
Process pre-quantized weights before applying them to the model
Args: