[Refactor] Replace activation: str with MoEActivation enum (#33843)

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2026-02-11 20:29:32 -05:00
committed by GitHub
parent 83b47f67b1
commit ff1f83b056
48 changed files with 474 additions and 282 deletions

View File

@@ -11,6 +11,7 @@ import torch
import vllm.model_executor.layers.fused_moe.modular_kernel as mk
from tests.kernels.moe.utils import make_dummy_moe_config
from vllm import _custom_ops as ops
from vllm.model_executor.layers.fused_moe.activation import MoEActivation
from vllm.model_executor.layers.fused_moe.config import fp8_w8a8_moe_quant_config
from vllm.model_executor.layers.fused_moe.cutlass_moe import CutlassExpertsFp8
from vllm.model_executor.layers.fused_moe.fused_moe import fused_experts, fused_topk
@@ -161,7 +162,7 @@ def bench_run(
w2_fp8q_cutlass,
topk_weights,
topk_ids,
activation="silu",
activation=MoEActivation.SILU,
global_num_experts=num_experts,
)
torch.cuda.synchronize()