xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-14 18:37:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

change top level interface to mk

Browse Source
This commit is contained in:
Yongye Zhu 2025-12-19 22:16:28 +00:00
parent f790068600
commit 60279d272e
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/layers/fused_moe/unquantized_fused_moe_method.py
View File

@ -31,6 +31,10 @@ from vllm.model_executor.utils import set_weight_attrs
from vllm.platforms import current_platform
from vllm.platforms.interface import CpuArchEnum
from vllm.utils.flashinfer import has_flashinfer_cutlass_fused_moe
import vllm.model_executor.layers.fused_moe.modular_kernel as mk
from vllm.model_executor.layers.fused_moe.prepare_finalize import (
MoEPrepareAndFinalizeNoEP,
)
if current_platform.is_cuda_alike():
from .fused_batched_moe import BatchedTritonExperts