[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:
bnellnm
2026-07-31 11:28:18 +01:00
committed by GitHub
co-authored by Harry Mellor
parent c911120a6f
commit 6e311c6e20
80 changed files with 243 additions and 234 deletions
@@ -18,7 +18,7 @@ from vllm.distributed import (
from vllm.forward_context import get_forward_context
from vllm.logger import init_logger
from vllm.model_executor.layers.fused_moe import (
FusedMoE,
FusedMoEFactory,
fused_moe_make_expert_params_mapping,
)
from vllm.model_executor.layers.layernorm import RMSNorm
@@ -329,8 +329,8 @@ class BailingMoeV25(nn.Module):
else:
self.shared_experts = None
# Routed experts using FusedMoE
self.experts = FusedMoE(
# Routed experts using FusedMoEFactory
self.experts = FusedMoEFactory(
shared_experts=self.shared_experts,
num_experts=self.num_experts,
top_k=self.top_k,
@@ -602,7 +602,7 @@ class BailingMoeV25Model(nn.Module):
(".gate_up_proj", ".up_proj", 1),
]
# Expert parameter mappings from FusedMoE
# Expert parameter mappings from FusedMoEFactory
expert_mappings = list(self.get_expert_mapping())
def load_param(name: str, tensor: torch.Tensor, shard_id=None) -> bool: