[Bugfix] Allow shared_experts skip quantization for DeepSeekV2/V3 (#14100)

Signed-off-by: mgoin <mgoin64@gmail.com>

vllm/model_executor/models/deepseek_v2.py

@@ -145,6 +145,7 @@ class DeepseekV2MoE(nn.Module):
                 hidden_act=config.hidden_act,
                 quant_config=quant_config,
                 reduce_results=False,
+                prefix=f"{prefix}.shared_experts",
             )
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: