[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)
Signed-off-by: Bill Nell <bnell@redhat.com> Signed-off-by: bnellnm <49004751+bnellnm@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -43,7 +43,7 @@ from vllm.model_executor.layers.attention import (
|
||||
Attention,
|
||||
StaticSinkAttention,
|
||||
)
|
||||
from vllm.model_executor.layers.fused_moe import FusedMoE
|
||||
from vllm.model_executor.layers.fused_moe import FusedMoEFactory
|
||||
from vllm.model_executor.layers.layernorm import RMSNorm
|
||||
from vllm.model_executor.layers.linear import (
|
||||
ColumnParallelLinear,
|
||||
@@ -195,7 +195,7 @@ class OpenPanguMoE(nn.Module):
|
||||
else:
|
||||
self.shared_experts = None
|
||||
|
||||
self.experts = FusedMoE(
|
||||
self.experts = FusedMoEFactory(
|
||||
shared_experts=self.shared_experts,
|
||||
num_experts=config.n_routed_experts,
|
||||
top_k=config.num_experts_per_tok,
|
||||
|
||||
Reference in New Issue
Block a user