Commit c345225e authored by raojy's avatar raojy 💬
Browse files

Update README.md

parent 2c86d258
......@@ -61,7 +61,7 @@ docker run -it \
#### 单机推理
```bash
## serve启动
vllm serve Qwen/Qwen3.6-35B-A3B \
vllm serve Qwen/Qwen3.6-27B \
--port 8001 \
--trust-remote-code \
--dtype bfloat16 \
......@@ -71,15 +71,29 @@ vllm serve Qwen/Qwen3.6-35B-A3B \
--tool-call-parser qwen3_coder
## client访问
curl -X POST "http://localhost:8001/v1/chat/completions" -H "Content-Type: application/json" -d '{
"model": "Qwen/Qwen3.6-35B-A3B",
curl http://localhost:8001/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen3.6-27B",
"messages": [
{"role": "system", "content": "你是一个有用的助手。"},
{"role": "user", "content": "你好,请做一下简单的自我介绍。"}
{"role": "user", "content": "帮我查询上海的天气"}
],
"max_tokens": 512,
"temperature": 0.7,
"stream": false
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "查询城市天气",
"parameters": {
"type": "object",
"properties": {
"city": {"type": "string"}
},
"required": ["city"]
}
}
}
]
}'
```
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment