apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

dcu adapter ernie45t (#2756)

Browse Source 
Co-authored-by: lifu <lifu@sugon.com>
Co-authored-by: yongqiangma <xing.wo@163.com>
This commit is contained in:
lifulll
2025-07-09 18:56:27 +08:00
committed by GitHub
parent 03a74995b8
commit 1f28bdf994
30 changed files with 1133 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
fastdeploy/model_executor/layers/quantization/weight_only.py
View File

@@ -75,6 +75,15 @@ class WeightOnlyConfig(QuantConfigBase):
return GCUWeightOnlyMoEMethod(self)
else:
return GCUWeightOnlyLinearMethod(self)
elif current_platform.is_dcu():
if isinstance(layer, FusedMoE):
from fastdeploy.model_executor.layers.backends import (
DCUTritonWeightOnlyMoEMethod)
return DCUTritonWeightOnlyMoEMethod(self)
else:
from fastdeploy.model_executor.layers.backends import (
DCUWeightOnlyLinearMethod)
return DCUWeightOnlyLinearMethod(self)
else:
if isinstance(layer, FusedMoE):
if layer.use_method == "cutlass":