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

fix w4afp8_gemm_scale_permute import error on A100 (#3611)

Browse Source
This commit is contained in:
Yuan Xiaolan
2025-08-28 11:42:23 +08:00
committed by GitHub
parent ad9b95e6dd
commit d37331fc71
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fastdeploy/model_executor/layers/moe/fused_moe_cutlass_backend.py
View File

@@ -31,8 +31,12 @@ if current_platform.is_cuda():
moe_expert_dispatch, moe_expert_dispatch,
moe_expert_reduce, moe_expert_reduce,
noaux_tc, noaux_tc,
w4afp8_gemm_scale_permute,
) )
try:
from fastdeploy.model_executor.ops.gpu import w4afp8_gemm_scale_permute
except:
logger.warning("import w4afp8_gemm_scale_permute Failed!")
elif current_platform.is_iluvatar(): elif current_platform.is_iluvatar():
from fastdeploy.model_executor.ops.iluvatar import ( from fastdeploy.model_executor.ops.iluvatar import (
moe_expert_dispatch, moe_expert_dispatch,