[PP] qwen3 vl skip layer id for pp (#19135)

python/sglang/srt/models/qwen3_vl_moe.py

@@ -26,6 +26,7 @@ from sglang.srt.configs.qwen3_vl import Qwen3VLMoeConfig, Qwen3VLMoeTextConfig
 from sglang.srt.eplb.expert_location import ModelConfigForExpertLocation
 from sglang.srt.layers.moe.fused_moe_triton.layer import FusedMoE
 from sglang.srt.layers.quantization.base_config import QuantizationConfig
+from sglang.srt.layers.utils import get_layer_id
 from sglang.srt.model_executor.forward_batch_info import ForwardBatch, PPProxyTensors
 from sglang.srt.model_loader.weight_utils import default_weight_loader
 from sglang.srt.models.qwen3_moe import Qwen3MoeDecoderLayer, Qwen3MoeModel
@@ -230,6 +231,17 @@ class Qwen3VLMoeForConditionalGeneration(Qwen3VLForConditionalGeneration):
 
         for name, loaded_weight in weights:
             name = name.replace(r"model.language_model.", r"model.")
+            layer_id = get_layer_id(name)
+            if (
+                "visual" not in name
+                and layer_id is not None
+                and hasattr(self.model, "start_layer")
+                and (
+                    layer_id < self.model.start_layer
+                    or layer_id >= self.model.end_layer
+                )
+            ):
+                continue
 
             for param_name, weight_name, shard_id in stacked_params_mapping:
                 if "experts.gate_up_proj" in name or "experts.down_proj" in name: