From f0339022c180c8d781228ab7694e23206a3c4f0b Mon Sep 17 00:00:00 2001
From: ViperEkura <3081035982@qq.com>
Date: Thu, 14 May 2026 20:59:01 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20batch=20=E6=8E=A8=E7=90=86=E7=A4=BA?=
 =?UTF-8?q?=E4=BE=8B=E6=B7=BB=E5=8A=A0=20chat=20template=20=E5=92=8C=20sys?=
 =?UTF-8?q?tem=20prompt?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 新增 prompts 列表，对每个输入应用 apply_chat_template
- 添加 system message 到对话模板
---
 scripts/demo/generate_batch.py | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/scripts/demo/generate_batch.py b/scripts/demo/generate_batch.py
index a074976..39c4975 100644
--- a/scripts/demo/generate_batch.py
+++ b/scripts/demo/generate_batch.py
@@ -24,12 +24,23 @@ def batch_generate():
         "请问什么是显卡",
     ]
 
+    prompts = [
+        tokenizer.apply_chat_template(
+            [
+                {"role": "system", "content": "You are a helpful assistant."},
+                {"role": "user", "content": q},
+            ],
+            tokenize=False,
+        )
+        for q in inputs
+    ]
+
     engine = InferenceEngine(
         model=model,
         tokenizer=tokenizer,
     )
     responses = engine.generate(
-        prompt=inputs,
+        prompt=prompts,
         stream=False,
         max_tokens=2048,
         temperature=0.8,