x

test.py

@@ -0,0 +1,19 @@
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="http://192.168.0.11:8000/v1",
+    api_key="dummy"  # vLLM 不需要真实的 API key
+)
+
+# 聊天完成
+response = client.chat.completions.create(
+    model="/opt/model/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit",
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "你好，请介绍一下你自己"}
+    ],
+    max_tokens=500,
+    temperature=0.7
+)
+
+print(response.choices[0].message.content)