[Kernel] Add b12x FP4 MoE backend (#52018)
Signed-off-by: Luke Alonso <lalonso@gmail.com> Signed-off-by: mgoin <mgoin64@gmail.com> Signed-off-by: Misha Goin <mgoin64@gmail.com> Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
@@ -376,6 +376,7 @@ class GptOssMxfp4MoEMethod(FusedMoEMethodBase):
|
||||
experts_cls=self.experts_cls,
|
||||
routing_tables=layer._expert_routing_tables(),
|
||||
)
|
||||
self.moe_kernel.fused_experts.process_weights_after_loading(layer)
|
||||
|
||||
def process_weights_after_loading(self, layer: RoutedExperts) -> None:
|
||||
w13 = layer.w13_weight
|
||||
@@ -769,6 +770,7 @@ class Mxfp4MoEMethod(FusedMoEMethodBase):
|
||||
experts_cls=self.experts_cls,
|
||||
routing_tables=layer._expert_routing_tables(),
|
||||
)
|
||||
self.moe_kernel.fused_experts.process_weights_after_loading(layer)
|
||||
|
||||
def process_weights_after_loading(self, layer):
|
||||
w13 = layer.w13_weight
|
||||
|
||||
Reference in New Issue
Block a user