A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 08:30 UTC
[BugFix] Fix import error for fused_moe (#18642)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
wangxiyuan committed
May 24, 2025 at 22:53 UTC
b9018a3f9f81031fea0cf228f502a6d1c64b7a5f
1 file changed
+1
vllm/model_executor/layers/fused_moe/layer.py
+1
@@ -41,6 +41,7 @@ if current_platform.is_cuda_alike():
41
from .pplx_prepare_finalize import PplxPrepareAndFinalize
42
else:
43
fused_experts = None # type: ignore
44
+ FusedMoEPermuteExpertsUnpermute = None # type: ignore
45
FusedMoEPrepareAndFinalize = None # type: ignore
46
if is_rocm_aiter_moe_enabled():
47
from vllm.model_executor.layers.fused_moe.rocm_aiter_fused_moe import ( # noqa: E501