[MoE Refactor] Combine CompressedTensorsWNA16MarlinMoEMethod with CompressedTensorsWNA16MoEMethod (#44570)
Signed-off-by: Bill Nell <bnell@redhat.com> Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com> Signed-off-by: Dobrzyniewicz, Agata <agata.dobrzyniewicz@intel.com> Signed-off-by: Tushar Jain <tushar00jain@users.noreply.github.com> Signed-off-by: yewentao256 <zhyanwentao@126.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Taneem Ibrahim <taneem.ibrahim@gmail.com> Co-authored-by: Agata Dobrzyniewicz <160237065+adobrzyn@users.noreply.github.com> Co-authored-by: Tushar Jain <8455015+tushar00jain@users.noreply.github.com> Co-authored-by: Tushar Jain <tushar00jain@users.noreply.github.com> Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com> Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
This commit is contained in:
co-authored by
Claude
Taneem Ibrahim
Agata Dobrzyniewicz
Tushar Jain
Tushar Jain
Wentao Ye
Jiangyun Zhu
parent
0c4dc7c488
commit
454ea5b526
@@ -778,16 +778,6 @@ class ModelOptFp8MoEMethod(FusedMoEMethodBase):
|
||||
"logic. This function should not be called."
|
||||
)
|
||||
|
||||
def select_gemm_impl(
|
||||
self,
|
||||
prepare_finalize: mk.FusedMoEPrepareAndFinalizeModular,
|
||||
layer: RoutedExperts,
|
||||
) -> mk.FusedMoEExpertsModular:
|
||||
raise ValueError(
|
||||
f"{self.__class__.__name__} uses the new modular kernel initialization "
|
||||
"logic. This function should not be called."
|
||||
)
|
||||
|
||||
def create_weights(
|
||||
self,
|
||||
layer: RoutedExperts,
|
||||
@@ -2104,16 +2094,6 @@ class ModelOptMxFp8FusedMoE(FusedMoEMethodBase):
|
||||
"logic. This function should not be called."
|
||||
)
|
||||
|
||||
def select_gemm_impl(
|
||||
self,
|
||||
prepare_finalize: mk.FusedMoEPrepareAndFinalizeModular,
|
||||
layer: RoutedExperts,
|
||||
) -> mk.FusedMoEExpertsModular:
|
||||
raise ValueError(
|
||||
f"{self.__class__.__name__} uses the new modular kernel initialization "
|
||||
"logic. This function should not be called."
|
||||
)
|
||||
|
||||
def get_fused_moe_quant_config(
|
||||
self, layer: RoutedExperts
|
||||
) -> FusedMoEQuantConfig | None:
|
||||
|
||||
Reference in New Issue
Block a user