From a4781c9fe5180ca46b238318ace3102cc7c4e942 Mon Sep 17 00:00:00 2001
From: ZeyuanChen2000 <806126546@qq.com>
Date: Mon, 14 Sep 2026 14:37:44 +0800
Subject: [PATCH] [NPU] Fix error due to missing parameter quant_linear passing
 (#37384)

---
 python/sglang/srt/layers/quantization/modelslim/modelslim.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/python/sglang/srt/layers/quantization/modelslim/modelslim.py b/python/sglang/srt/layers/quantization/modelslim/modelslim.py
index 3e1500b06..338cee224 100644
--- a/python/sglang/srt/layers/quantization/modelslim/modelslim.py
+++ b/python/sglang/srt/layers/quantization/modelslim/modelslim.py
@@ -63,6 +63,7 @@ def npu_wrapper_rmsnorm_forward(func):
         x: torch.Tensor,
         residual: Optional[torch.Tensor] = None,
         post_residual_addition: Optional[torch.Tensor] = None,
+        **kwargs,
     ) -> Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]]:
         if not x.is_contiguous():
             x = x.contiguous()