From 97e3b8998dc0f331423438091067ec0201d35e54 Mon Sep 17 00:00:00 2001
From: Jimmy Shong <69131491+Jiminator@users.noreply.github.com>
Date: Thu, 18 Jun 2026 05:04:25 -0700
Subject: [PATCH] Pass quant_config to attention gate projection (#28649)

---
 python/sglang/srt/models/laguna.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/python/sglang/srt/models/laguna.py b/python/sglang/srt/models/laguna.py
index 57bded6ba..691f835ae 100644
--- a/python/sglang/srt/models/laguna.py
+++ b/python/sglang/srt/models/laguna.py
@@ -304,7 +304,7 @@ class LagunaAttention(nn.Module):
                 g_proj_dim,
                 bias=False,
                 gather_output=False,
-                quant_config=None,
+                quant_config=quant_config,
                 tp_rank=attn_tp_rank,
                 tp_size=attn_tp_size,
                 prefix=add_prefix("g_proj", prefix),