[Quantization] Fix Humming RoutedExperts import (#43540)
Signed-off-by: Minh Vu <vuhoangminh97@gmail.com> Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
@@ -8,11 +8,11 @@ from humming.layer import HummingInputSchema, HummingMethod
|
|||||||
from humming.schema import BaseWeightSchema
|
from humming.schema import BaseWeightSchema
|
||||||
|
|
||||||
from vllm import envs
|
from vllm import envs
|
||||||
|
from vllm.model_executor.layers.fused_moe import RoutedExperts
|
||||||
from vllm.model_executor.layers.fused_moe.config import (
|
from vllm.model_executor.layers.fused_moe.config import (
|
||||||
FusedMoEQuantConfig,
|
FusedMoEQuantConfig,
|
||||||
FusedMoEQuantDesc,
|
FusedMoEQuantDesc,
|
||||||
)
|
)
|
||||||
from vllm.model_executor.layers.fused_moe.routed_experts import RoutedExperts
|
|
||||||
from vllm.model_executor.layers.linear import LinearBase
|
from vllm.model_executor.layers.linear import LinearBase
|
||||||
from vllm.model_executor.layers.quantization.utils.quant_utils import GroupShape
|
from vllm.model_executor.layers.quantization.utils.quant_utils import GroupShape
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user