[Bugfix] fix IMA issue in certain cases of the moe marlin kernel (#28619)

Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

vllm/model_executor/layers/fused_moe/shared_fused_moe.py

@@ -38,7 +38,6 @@ class SharedFusedMoE(FusedMoE):
                 # TODO(wentao): find the root cause and remove this condition
                 self.enable_eplb
                 or (self.moe_config.use_flashinfer_cutlass_kernels and self.dp_size > 1)
-                or self.use_marlin_kernels
             )
             and self._shared_experts is not None
         )