frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Lazy import fused_experts in BitsAndBytesMoEMethod to avoid break not-cuda-alike devices (#20822)

Browse Source 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang
2025-07-12 11:52:05 +08:00
committed by GitHub
parent 44d02f54db
commit b1235c3e10
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/quantization/bitsandbytes.py
View File

@ -5,7 +5,6 @@ from typing import Any, Callable, Optional, Union
import torch
from vllm.model_executor.layers.fused_moe import fused_experts
from vllm.model_executor.layers.fused_moe.layer import (FusedMoE,
FusedMoEMethodBase)
from vllm.model_executor.layers.linear import (LinearBase, LinearMethodBase,
@ -467,6 +466,7 @@ class BitsAndBytesMoEMethod(FusedMoEMethodBase):
logical_to_physical_map: Optional[torch.Tensor] = None,
logical_replica_count: Optional[torch.Tensor] = None,
) -> torch.Tensor:
from vllm.model_executor.layers.fused_moe import fused_experts
if enable_eplb:
raise NotImplementedError(