[MoE Refactor] Move the shared/fused expert output sum into MoERunnerBase (#35949)

Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
This commit is contained in:
bnellnm
2026-04-20 12:28:46 -04:00
committed by GitHub
co-authored by Robert Shaw
parent 595562651a
commit 726efe177b
52 changed files with 325 additions and 700 deletions
-3
View File
@@ -592,9 +592,6 @@ class FusedMoEWithLoRA(BaseLayerWithLoRA):
def forward(self, *args, **kwargs):
return self.base_layer.forward(*args, **kwargs)
def maybe_all_reduce_tensor_model_parallel(self, *args, **kwargs):
return self.base_layer.maybe_all_reduce_tensor_model_parallel(*args, **kwargs)
@property
def quant_method(self):
return self.base_layer.quant_method