[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:
@@ -189,7 +189,6 @@ class MLPBlock(torch.nn.Module):
|
||||
top_k=config.num_experts_per_tok,
|
||||
hidden_size=config.hidden_size,
|
||||
intermediate_size=config.intermediate_size,
|
||||
reduce_results=True,
|
||||
renormalize=True,
|
||||
quant_config=quant_config,
|
||||
prefix=f"{prefix}.experts",
|
||||
|
||||
Reference in New Issue
Block a user