[Core] FlashInfer CUTLASS fused MoE backend (NVFP4) (#20037)

Signed-off-by: shuw <shuw@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

vllm/model_executor/layers/fused_moe/fused_moe.py

@@ -1646,6 +1646,7 @@ class TritonExperts(mk.FusedMoEPermuteExpertsUnpermute):
         workspace2: torch.Tensor,
         expert_tokens_meta: Optional[mk.ExpertTokensMetadata],
         apply_router_weight_on_input: bool,
+        extra_expert_args: Optional[dict[str, Any]],
     ):
         # Check constraints.
         if self.use_int4_w4a16: