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

[GCU] Support gcu platform (#2702)

Browse Source 
baseline: e7fa57ebae

Co-authored-by: yongqiangma <xing.wo@163.com>
This commit is contained in:
EnflameGCU
2025-07-08 13:00:52 +08:00
committed by GitHub
parent 26d5d737dd
commit d0f4d6ba3a
33 changed files with 2988 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
fastdeploy/model_executor/layers/quantization/weight_only.py
View File

@@ -66,6 +66,13 @@ class WeightOnlyConfig(QuantConfigBase):
return XPUWeightOnlyMoEMethod(self)
else:
return XPUWeightOnlyLinearMethod(self)
elif current_platform.is_gcu():
from fastdeploy.model_executor.layers.backends import (
GCUWeightOnlyLinearMethod, GCUWeightOnlyMoEMethod)
if isinstance(layer, FusedMoE):
return GCUWeightOnlyMoEMethod(self)
else:
return GCUWeightOnlyLinearMethod(self)
else:
if isinstance(layer, FusedMoE):
if layer.use_method == "cutlass":