Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion vllm/model_executor/layers/quantization/bitsandbytes.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,6 @@

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,
Expand Down Expand Up @@ -467,6 +466,7 @@ def apply(
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
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Moving the import here fixes the issue, but it would be beneficial to add a comment explaining why the import is done locally within the function. This can help future developers understand the reasoning behind this change and prevent accidental regressions.


if enable_eplb:
raise NotImplementedError(
Expand Down