biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/kernels/moe/test_pplx_cutlass_moe.py
View File

@@ -9,6 +9,7 @@ from tests.kernels.utils import torch_experts
from vllm import _custom_ops as ops
from vllm.config import VllmConfig, set_current_vllm_config
from vllm.model_executor.layers.fused_moe import fused_topk
from vllm.model_executor.layers.fused_moe.activation import MoEActivation
from vllm.model_executor.layers.fused_moe.config import (
FusedMoEConfig,
FusedMoEParallelConfig,
@@ -149,7 +150,7 @@ def pplx_cutlass_moe(
num_local_experts=num_local_experts,
num_logical_experts=num_experts,
moe_parallel_config=FusedMoEParallelConfig.make_no_parallel(),
activation="silu",
activation=MoEActivation.SILU,
in_dtype=torch.bfloat16,
device="cuda",
routing_method=RoutingMethodType.Llama4,