[MoE Refactor] Make SharedExperts class for use with DefaultMoERunner (#35153)
Signed-off-by: Bill Nell <bnell@redhat.com>
This commit is contained in:
@@ -483,7 +483,7 @@ class BitsAndBytesMoEMethod(FusedMoEMethodBase):
|
||||
topk_weights: torch.Tensor,
|
||||
topk_ids: torch.Tensor,
|
||||
shared_experts_input: torch.Tensor | None,
|
||||
) -> torch.Tensor | tuple[torch.Tensor, torch.Tensor]:
|
||||
) -> torch.Tensor:
|
||||
from vllm.model_executor.layers.fused_moe import fused_experts
|
||||
|
||||
# TODO(bnell): Do these need to be called on the hot path?
|
||||
|
||||
Reference in New Issue
Block a user