[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
@@ -490,8 +490,9 @@ class AutoGPTQMoEMethod(FusedMoEMethodBase):
|
||||
moe,
|
||||
weight_key,
|
||||
quant_config=self.quant_config,
|
||||
may_have_zp=True,
|
||||
may_have_zp=not self.quant_config.is_sym,
|
||||
may_have_bias=True,
|
||||
allow_tile_padding=not self.quant_config.desc_act,
|
||||
)
|
||||
|
||||
def create_weights(
|
||||
@@ -806,16 +807,6 @@ class AutoGPTQMoEMethod(FusedMoEMethodBase):
|
||||
w2_bias=getattr(layer, "w2_bias", None),
|
||||
)
|
||||
|
||||
def select_gemm_impl(
|
||||
self,
|
||||
prepare_finalize,
|
||||
layer: RoutedExperts,
|
||||
):
|
||||
raise ValueError(
|
||||
f"{self.__class__.__name__} uses the new modular kernel "
|
||||
"initialization logic. This function should not be called."
|
||||
)
|
||||
|
||||
def apply(
|
||||
self,
|
||||
layer: RoutedExperts,
|
||||
|
||||
Reference in New Issue
Block a user