Service - Platform For AI - Alibaba Cloud Documentation Center

Parameter	Type	Description	Example
	object	The details of the service.
RequestId	string	The request ID.	40325405-579C-4D82********
Region	string	The region where the service is deployed.	cn-shanghai
CallerUid	string	The UID of the account that created the service.	20123*******
ParentUid	string	The UID of the primary account used to create the service.	11234*******
CurrentVersion	integer	The current version of the running model.	1
Cpu	integer	The number of CPU cores requested for each instance.	1
Gpu	integer	The number of GPUs requested for each instance.	0
Image	string	The image used by the service.	registry.cn-shanghai.aliyuncs.com/eas/echo_cn-shanghai:v0.0.1-20210129111320
PendingInstance	integer	The number of pending instances for the service.	0
RunningInstance	integer	The number of running instances of the service.	1
TotalInstance	integer	The total number of instances for the service.	1
InternetEndpoint	string	The internet endpoint of the service. This field is returned only by the `DescribeService` operation.	http://10123*****.cn-shanghai.aliyuncs.com/api/predict/echo
IntranetEndpoint	string	The intranet endpoint of the service. This field is returned only by the `DescribeService` operation.	http://10123*****.vpc.cn-shanghai.aliyuncs.com/api/predict/echo
LatestVersion	integer	The latest version of the service.	1
Memory	integer	The amount of memory requested for each instance, in MB.	1024
Message	string	A message that provides information about the service status.	Service start successfully
Namespace	string	The namespace where the service is located.	echo
Reason	string	The reason for the service status.	RUNNING
Resource	string	The resource group to which the service belongs.	eas-r-xxxxxxx
ResourceAlias	string	The alias of the resource group to which the service belongs.	my_resource
ServiceConfig	string	The configuration of the service.	{"metadata":{"cpu":1,"instance":1,"memory":1024},"name":"echo","processor_entry":"libecho.so","processor_path":"http://oss-cn-hangzhou-zmf.aliyuncs.com/059247/echo_processor_release.tar.gz","processor_type":"cpp"}
ServiceName	string	The name of the service.	echo
ServiceGroup	string	The group to which the service belongs.	my_group
Status	string	The status of the service.	Running
CreateTime	string	The time when the service was created, in RFC 3339 format (UTC).	2021-01-29T11:13:20Z
UpdateTime	string	The time when the service was last updated, in RFC 3339 format (UTC).	2021-01-29T11:13:20Z
Weight	integer	The traffic weight for the canary release of the service.	100
ServiceId	string	The unique ID of the service.	eas-m-xxasdat
ServiceUid	string	The service ID. This value is the same as `ServiceId`.	eas-m-xxasdat
AccessToken	string	The access token for the service.	MzJiMDI5MDliODc0MTlkYmI0ZDhlYmExYjczYTIyZTE3Zm********
Source	string	The deployment source of the service.	dsw
ExtraData	string	Additional information about the service.	{"blue_green_services":["test","testxxxx"]}
Role	string	The role of the service.	Queue
RoleAttrs	string	Additional attributes of the service role. This field is returned only by the `DescribeService` operation.	{"ApproxMaxLength":null,"Length":null,"MaxPayloadBytes":null}
SafetyLock	string	The safety lock status of the service.	dangerous
SecondaryInternetEndpoint	string	The internet endpoint for synchronous requests to an asynchronous service. This field is returned only by the `DescribeService` operation.	http://10123*****.cn-shanghai.aliyuncs.com/api/predict/async_path.echo
SecondaryIntranetEndpoint	string	The intranet endpoint for synchronous requests to an asynchronous service. This field is returned only by the `DescribeService` operation.	http://10123*****.vpc.cn-shanghai.aliyuncs.com/api/predict/async_path.echo
Labels	array	The labels of the service.
	object
LabelKey	string	The key of the service label.	key1
LabelValue	string	The value of the service label.	value1
WorkspaceId	string	The ID of the workspace to which the service belongs.	123445
AppType	string	The application type of the service.	LLM
AppConfig	string	The application configuration for the service.	{"ModelStorage":"oss"}
AppSpecName	string	The application specification name for the service.	llama_7b_fp16
AppVersion	string	The application version of the service.	v1
TrafficState	string	The traffic state of the service.	standalone
QuotaId	string	The quota ID of the service. This field is returned only for services that are deployed on a Lingjun resource quota.	quotaxxxxx
Gateway	string	The ID of the dedicated gateway for the service. This field is returned only for services that are bound to a dedicated gateway.	gw-xxxxxx
GPUMemory	integer	The amount of GPU memory requested for each instance when GPU sharing is enabled.	20
GPUCorePercentage	integer	The percentage of GPU computing power requested for each instance when GPU sharing is enabled.	50
ResourceBurstable	boolean	Indicates whether a burstable resource pool is enabled for the service.	true
CronscalerEnabled	boolean	Indicates whether scheduled scaling is enabled for the service.	true
AutoscalerEnabled	boolean	Indicates whether auto scaling is enabled for the service.	true
InstanceCountInResource	object	A breakdown of the instance count by resource type.
Public	integer	The number of instances that use public resource groups.	10
Dedicated	integer	The number of instances that use dedicated or self-managed resource groups.	10
Quota	integer	The number of instances that use a Lingjun quota.	10
WorkloadType	string

object

The details of the service.

RequestId

string

The request ID.

40325405-579C-4D82********

Region

string

The region where the service is deployed.

cn-shanghai

CallerUid

string

The UID of the account that created the service.

20123*******

ParentUid

string

The UID of the primary account used to create the service.

11234*******

CurrentVersion

integer

The current version of the running model.

1

Cpu

integer

The number of CPU cores requested for each instance.

1

Gpu

integer

The number of GPUs requested for each instance.

0

Image

string

The image used by the service.

registry.cn-shanghai.aliyuncs.com/eas/echo_cn-shanghai:v0.0.1-20210129111320

PendingInstance

integer

The number of pending instances for the service.

0

RunningInstance

integer

The number of running instances of the service.

1

TotalInstance

integer

The total number of instances for the service.

1

InternetEndpoint

string

The internet endpoint of the service. This field is returned only by the DescribeService operation.

http://10123*****.cn-shanghai.aliyuncs.com/api/predict/echo

IntranetEndpoint

string

The intranet endpoint of the service. This field is returned only by the DescribeService operation.

http://10123*****.vpc.cn-shanghai.aliyuncs.com/api/predict/echo

LatestVersion

integer

The latest version of the service.

1

Memory

integer

The amount of memory requested for each instance, in MB.

1024

Message

string

A message that provides information about the service status.

Service start successfully

Namespace

string

The namespace where the service is located.

echo

Reason

string

The reason for the service status.

RUNNING

Resource

string

The resource group to which the service belongs.

eas-r-xxxxxxx

ResourceAlias

string

The alias of the resource group to which the service belongs.

my_resource

ServiceConfig

string

The configuration of the service.

{"metadata":{"cpu":1,"instance":1,"memory":1024},"name":"echo","processor_entry":"libecho.so","processor_path":"http://oss-cn-hangzhou-zmf.aliyuncs.com/059247/echo_processor_release.tar.gz","processor_type":"cpp"}

ServiceName

string

The name of the service.

echo

ServiceGroup

string

The group to which the service belongs.

my_group

Status

string

The status of the service.

Running

CreateTime

string

The time when the service was created, in RFC 3339 format (UTC).

2021-01-29T11:13:20Z

UpdateTime

string

The time when the service was last updated, in RFC 3339 format (UTC).

2021-01-29T11:13:20Z

Weight

integer

The traffic weight for the canary release of the service.

100

ServiceId

string

The unique ID of the service.

eas-m-xxasdat

ServiceUid

string

The service ID. This value is the same as ServiceId.

eas-m-xxasdat

AccessToken

string

The access token for the service.

MzJiMDI5MDliODc0MTlkYmI0ZDhlYmExYjczYTIyZTE3Zm********

Source

string

The deployment source of the service.

dsw

ExtraData

string

Additional information about the service.

{"blue_green_services":["test","testxxxx"]}

Role

string

The role of the service.

Queue

RoleAttrs

string

Additional attributes of the service role. This field is returned only by the DescribeService operation.

{"ApproxMaxLength":null,"Length":null,"MaxPayloadBytes":null}

SafetyLock

string

The safety lock status of the service.

dangerous

SecondaryInternetEndpoint

string

The internet endpoint for synchronous requests to an asynchronous service. This field is returned only by the DescribeService operation.

http://10123*****.cn-shanghai.aliyuncs.com/api/predict/async_path.echo

SecondaryIntranetEndpoint

string

The intranet endpoint for synchronous requests to an asynchronous service. This field is returned only by the DescribeService operation.

http://10123*****.vpc.cn-shanghai.aliyuncs.com/api/predict/async_path.echo

Labels

array

The labels of the service.

object

LabelKey

string

The key of the service label.

key1

LabelValue

string

The value of the service label.

value1

WorkspaceId

string

The ID of the workspace to which the service belongs.

123445

AppType

string

The application type of the service.

LLM

AppConfig

string

The application configuration for the service.

{"ModelStorage":"oss"}

AppSpecName

string

The application specification name for the service.

llama_7b_fp16

AppVersion

string

The application version of the service.

v1

TrafficState

string

The traffic state of the service.

standalone

QuotaId

string

The quota ID of the service. This field is returned only for services that are deployed on a Lingjun resource quota.

quotaxxxxx

Gateway

string

The ID of the dedicated gateway for the service. This field is returned only for services that are bound to a dedicated gateway.

gw-xxxxxx

GPUMemory

integer

The amount of GPU memory requested for each instance when GPU sharing is enabled.

20

GPUCorePercentage

integer

The percentage of GPU computing power requested for each instance when GPU sharing is enabled.

50

ResourceBurstable

boolean

Indicates whether a burstable resource pool is enabled for the service.

true

CronscalerEnabled

boolean

Indicates whether scheduled scaling is enabled for the service.

true

AutoscalerEnabled

boolean

Indicates whether auto scaling is enabled for the service.

true

InstanceCountInResource

object

A breakdown of the instance count by resource type.

Public

integer

The number of instances that use public resource groups.

10

Dedicated

integer

The number of instances that use dedicated or self-managed resource groups.

10

Quota

integer

The number of instances that use a Lingjun quota.

10

WorkloadType

string