[Feature][Humming] Humming feature integration (#56685)
Signed-off-by: jinzhen.ljz <jinzhen.ljz@antgroup.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Codex <noreply@openai.com> Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
co-authored by
Codex
mgoin
parent
27757dde02
commit
7d99c2c4fd
@@ -389,7 +389,7 @@ class MoeWNA16Method(FusedMoEMethodBase):
|
||||
self, layer: RoutedExperts
|
||||
) -> FusedMoEQuantConfig | None:
|
||||
if self.wna16_backend == WNA16MoEBackend.HUMMING:
|
||||
from vllm.model_executor.layers.quantization.utils.humming_utils import (
|
||||
from vllm.model_executor.layers.quantization.utils.humming import (
|
||||
get_humming_moe_quant_config,
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user