[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:
@@ -35,9 +35,7 @@ from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
from vllm.model_executor.layers.attention import Attention
|
||||
from vllm.model_executor.layers.fused_moe import (
|
||||
FusedMoE,
|
||||
)
|
||||
from vllm.model_executor.layers.fused_moe import FusedMoEFactory
|
||||
from vllm.model_executor.layers.linear import (
|
||||
QKVParallelLinear,
|
||||
ReplicatedLinear,
|
||||
@@ -273,7 +271,7 @@ class PhiMoE(nn.Module):
|
||||
prefix=f"{prefix}.gate",
|
||||
)
|
||||
|
||||
self.experts = FusedMoE(
|
||||
self.experts = FusedMoEFactory(
|
||||
num_experts=num_experts,
|
||||
top_k=top_k,
|
||||
hidden_size=hidden_size,
|
||||
|
||||
Reference in New Issue
Block a user