From 789951a42ae895925e5d1e75b1a947bb11bf48d0 Mon Sep 17 00:00:00 2001
From: freedak <freedak@163.com>
Date: Mon, 21 Sep 2026 16:34:12 +0800
Subject: [PATCH] =?UTF-8?q?chore:=20=E5=8D=87=E7=BA=A7=20LLM=20=E8=87=B3?=
 =?UTF-8?q?=20Qwen3.6-35B-A3B-int4-AutoRound?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

模型文件已在服务器 /data/models 就位，容器 qwen36 接替 qwen35 运行，
served-model-name 为 qwen3.6-35b。已验证 enable_thinking 开关与
</think> 分隔符行为一致，RAG 链路正常。

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 app/config.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/app/config.py b/app/config.py
index 7be1dfa..ebdaab7 100644
--- a/app/config.py
+++ b/app/config.py
@@ -39,7 +39,7 @@ LLM_URL = os.getenv("LLM_URL", "http://localhost:7000/v1")
 EMBEDDING_MODEL = os.getenv("EMBEDDING_MODEL", "qwen3-embedding-0.6b")
 
 # LLM 模型名
-LLM_MODEL = os.getenv("LLM_MODEL", "qwen3.5-35b")
+LLM_MODEL = os.getenv("LLM_MODEL", "qwen3.6-35b")
 
 # ===== 索引参数 =====
 # embedding 批量大小