[Kernels] Overlap shared experts with send/recv (#23273)

Signed-off-by: Bill Nell <bnell@redhat.com>

vllm/model_executor/layers/quantization/awq_marlin.py

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
-from typing import Any, Callable, Optional
+from typing import Any, Callable, Optional, Union
 
 import torch
 from torch.nn import Parameter
@@ -505,7 +505,7 @@ class AWQMoEMethod(FusedMoEMethodBase):
         expert_load_view: Optional[torch.Tensor] = None,
         logical_to_physical_map: Optional[torch.Tensor] = None,
         logical_replica_count: Optional[torch.Tensor] = None,
-    ) -> torch.Tensor:
+    ) -> Union[torch.Tensor, tuple[torch.Tensor, torch.Tensor]]:
         assert self.fused_experts is None
 
         if enable_eplb: