[Model] Adding support for MSFT Phi-3.5-MoE (#7729)

Co-authored-by: Your Name <you@example.com>
Co-authored-by: Zeqi Lin <zelin@microsoft.com>
Co-authored-by: Zeqi Lin <Zeqi.Lin@microsoft.com>

vllm/model_executor/layers/quantization/fp8.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional
+from typing import Any, Callable, Dict, List, Optional
 
 import torch
 from torch.nn import Module
@@ -468,15 +468,18 @@ class Fp8MoEMethod(FusedMoEMethodBase):
                                                         requires_grad=False)
             return
 
-    def apply(self,
-              layer: torch.nn.Module,
-              x: torch.Tensor,
-              router_logits: torch.Tensor,
-              top_k: int,
-              renormalize: bool,
-              use_grouped_topk: bool,
-              topk_group: Optional[int] = None,
-              num_expert_group: Optional[int] = None) -> torch.Tensor:
+    def apply(
+        self,
+        layer: torch.nn.Module,
+        x: torch.Tensor,
+        router_logits: torch.Tensor,
+        top_k: int,
+        renormalize: bool,
+        use_grouped_topk: bool,
+        topk_group: Optional[int] = None,
+        num_expert_group: Optional[int] = None,
+        custom_routing_function: Optional[Callable] = None,
+    ) -> torch.Tensor:
 
         from vllm.model_executor.layers.fused_moe import fused_experts
 
@@ -487,7 +490,8 @@ class Fp8MoEMethod(FusedMoEMethodBase):
             top_k=top_k,
             renormalize=renormalize,
             topk_group=topk_group,
-            num_expert_group=num_expert_group)
+            num_expert_group=num_expert_group,
+            custom_routing_function=custom_routing_function)
 
         return fused_experts(x,
                              layer.w13_weight,