xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-13 07:07:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix FusedMoEPrepareAndFinalize for cuda-disalike backends (#18178)

Browse Source 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao 2025-05-15 14:16:31 +08:00 committed by GitHub
parent dd2a94596a
commit 70f8b96724
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/layers/fused_moe/layer.py
View File

@ -43,6 +43,7 @@ if current_platform.is_cuda_alike():
from .pplx_prepare_finalize import PplxPrepareAndFinalize
else:
fused_experts = None # type: ignore
FusedMoEPrepareAndFinalize = None # type: ignore
if is_rocm_aiter_moe_enabled():
from vllm.model_executor.layers.fused_moe.rocm_aiter_fused_moe import ( # noqa: E501
rocm_aiter_biased_group_topk as grouped_topk)