新增调度配置

POST

/system/inference/config

请求参数

Authorization

API Key

在 header 添加参数

FrontToken

示例：

FrontToken: ********************

Body 参数application/json必填

示例

{
    "createBy": "string",
    "createTime": "2019-08-24T14:15:22.123Z",
    "updateBy": "string",
    "updateTime": "2019-08-24T14:15:22.123Z",
    "remark": "string",
    "params": {
        "property1": {},
        "property2": {}
    },
    "id": 0,
    "schedulingGroupKey": "string",
    "team": "string",
    "modelType": "TO_TEXT",
    "isEnabled": true,
    "defaultModel": "string",
    "k8sConfigJson": "string",
    "metadataJson": "string",
    "billingConfig": "string",
    "supportedTasks": "string",
    "lwsConfigYaml": "string",
    "scalingAlgorithm": "string",
    "maxLorasPerInstance": 0,
    "podStartupTimeSeconds": 0,
    "slaTargetSeconds": 0,
    "slaTtftSeconds": 0,
    "slaQueueWaitMs": 0,
    "rpm": 0,
    "context": "string",
    "isDeepThink": true,
    "modelIntroduction": "string"
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST '/system/inference/config' \
--header 'FrontToken: <api-key>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "createBy": "string",
    "createTime": "2019-08-24T14:15:22.123Z",
    "updateBy": "string",
    "updateTime": "2019-08-24T14:15:22.123Z",
    "remark": "string",
    "params": {
        "property1": {},
        "property2": {}
    },
    "id": 0,
    "schedulingGroupKey": "string",
    "team": "string",
    "modelType": "TO_TEXT",
    "isEnabled": true,
    "defaultModel": "string",
    "k8sConfigJson": "string",
    "metadataJson": "string",
    "billingConfig": "string",
    "supportedTasks": "string",
    "lwsConfigYaml": "string",
    "scalingAlgorithm": "string",
    "maxLorasPerInstance": 0,
    "podStartupTimeSeconds": 0,
    "slaTargetSeconds": 0,
    "slaTtftSeconds": 0,
    "slaQueueWaitMs": 0,
    "rpm": 0,
    "context": "string",
    "isDeepThink": true,
    "modelIntroduction": "string"
}'

返回响应

🟢200成功

*/*

Body

示例

{
    "code": 0,
    "msg": "string",
    "data": {},
    "error": true,
    "success": true
}

修改于 2026-04-08 07:34:18

修改调度配置

getInfo_1