[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
+2 -2
View File
@@ -21,7 +21,7 @@ from vllm.model_executor.layers.attention.attention import (
Attention,
set_default_quant_scales,
)
from vllm.model_executor.layers.fused_moe import FusedMoE
from vllm.model_executor.layers.fused_moe import FusedMoEFactory
from vllm.model_executor.layers.quantization.fp8 import (
Fp8Config,
Fp8KVCacheMethod,
@@ -393,7 +393,7 @@ def test_fp8_reloading(
method.use_marlin = use_marlin
else:
layer = FusedMoE(
layer = FusedMoEFactory(
num_experts=1,
top_k=1,
hidden_size=1,