部署基模型服务

开发中

POST

/base

请求参数

Body 参数application/json

示例

{"modelId":"52e2d717-7f8a-49b1-bf7c-03165a2a2b58","namespace":"default","serviceType":"base","serviceName":"test","minScale":1,"maxScale":1,"backend":"vllm","backendVersion":"1.0.0","backendArgs":["--model=/model/model.ckpt"],"servedName":["/model/model.ckpt"],"labels":{"key":"value"},"workers":null,"cpu":null,"memory":null,"gpuType":null,"gpuCount":null,"apiKey":""}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST '/base' \
--header 'Content-Type: application/json' \
--data-raw '{"modelId":"52e2d717-7f8a-49b1-bf7c-03165a2a2b58","namespace":"default","serviceType":"base","serviceName":"test","minScale":1,"maxScale":1,"backend":"vllm","backendVersion":"1.0.0","backendArgs":["--model=/model/model.ckpt"],"servedName":["/model/model.ckpt"],"labels":{"key":"value"},"workers":null,"cpu":null,"memory":null,"gpuType":null,"gpuCount":null,"apiKey":""}'

返回响应

🟢200成功

application/json

Body

示例

{
    "code": 0,
    "data": "c6db613b-c43a-4801-8cef-17a4638d0fa9"
}

修改于 2025-09-08 01:46:04

获取模型服务详情

部署lora服务