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

[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375)

Browse Source 
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
This commit is contained in:
bnellnm
2026-02-05 13:07:18 -05:00
committed by GitHub
parent 1ee95841bd
commit a57c8228ff
37 changed files with 132 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/kernels/moe/test_moe.py
View File

@@ -18,7 +18,11 @@ from transformers import MixtralConfig
from transformers.models.mixtral.modeling_mixtral import MixtralSparseMoeBlock
import vllm.model_executor.layers.fused_moe # noqa
from tests.kernels.moe.utils import fused_moe, make_dummy_moe_config
from tests.kernels.moe.utils import (
fused_moe,
make_dummy_moe_config,
modular_triton_fused_moe,
)
from tests.kernels.utils import opcheck, stack_and_dev, torch_experts, torch_moe
from vllm._aiter_ops import rocm_aiter_ops
from vllm.config import VllmConfig, set_current_vllm_config
@@ -36,9 +40,6 @@ from vllm.model_executor.layers.fused_moe.fused_marlin_moe import (
batched_fused_marlin_moe,
fused_marlin_moe,
)
from vllm.model_executor.layers.fused_moe.fused_moe import (
modular_triton_fused_moe,
)
from vllm.model_executor.layers.quantization.utils.marlin_utils import (
marlin_permute_bias,
)