Remove padding_index from models that don't use it for better Transformers v5 compatibility (#35189)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

vllm/model_executor/models/qwen3_moe.py

@@ -443,7 +443,6 @@ class Qwen3MoeModel(nn.Module):
         eplb_config = parallel_config.eplb_config
         self.num_redundant_experts = eplb_config.num_redundant_experts
 
-        self.padding_idx = config.pad_token_id
         self.vocab_size = config.vocab_size
         self.config = config
         self.quant_config = quant_config