[MoE Refactor] Remove SharedFusedMoE class (#35782)
Signed-off-by: Bill Nell <bnell@redhat.com>
This commit is contained in:
@@ -24,7 +24,6 @@ from vllm.logger import init_logger
|
||||
from vllm.model_executor.layers.activation import SiluAndMul, SwigluStepAndMul
|
||||
from vllm.model_executor.layers.attention import Attention
|
||||
from vllm.model_executor.layers.fused_moe import FusedMoE
|
||||
from vllm.model_executor.layers.fused_moe.shared_fused_moe import SharedFusedMoE
|
||||
from vllm.model_executor.layers.layernorm import GemmaRMSNorm
|
||||
from vllm.model_executor.layers.linear import (
|
||||
ColumnParallelLinear,
|
||||
@@ -372,7 +371,7 @@ class FusedMoEBlock(nn.Module):
|
||||
quant_config=quant_config,
|
||||
prefix=f"{prefix}.share_expert",
|
||||
)
|
||||
self.experts = SharedFusedMoE(
|
||||
self.experts = FusedMoE(
|
||||
shared_experts=self.share_expert,
|
||||
gate=self.gate,
|
||||
num_experts=config.moe_num_experts,
|
||||
|
||||
Reference in New Issue
Block a user