[Bugfix] Fix Qwen2.5-VL quantized model weights loading (#23512)

Signed-off-by: Zifei Tong <zifeitong@gmail.com>

vllm/model_executor/models/qwen2_5_vl.py

@@ -852,6 +852,10 @@ class Qwen2_5_VLForConditionalGeneration(nn.Module, SupportsMultiModal,
                                          SupportsLoRA, SupportsPP,
                                          SupportsQuant):
 
+    packed_modules_mapping = {
+        "gate_up_proj": ["gate_proj", "up_proj"],
+    }
+
     # To ensure correct weight loading and mapping.
     hf_to_vllm_mapper = WeightsMapper(
         orig_to_new_prefix={