Adding a Deployment

Function

This API is used to deploy a model as a real-time service.

Debugging

You can debug this API through automatic authentication in API Explorer or use the SDK sample code generated by API Explorer.

Authorization Information

Each account has all the permissions required to call all APIs, but IAM users must be assigned the required permissions.

If you are using role/policy-based authorization, see Permissions Policies and Supported Actions for details on the required permissions.
If you are using identity policy-based authorization, the following identity policy-based permissions are required.

Action

Access Level

Resource Type (*: required)

Condition Key

Alias

Dependencies

modelarts:service:createDeployment

Read

service *

-

-

-

Action	Access Level	Resource Type (*: required)	Condition Key	Alias	Dependencies
modelarts:service:createDeployment	Read	service *	-	-	-

URI

POST /v2/{project_id}/services/{service_id}/deployments

**Table 1** Path Parameters
Parameter	Mandatory	Type	Description
project_id	Yes	String	Definition Project ID. For details, see Obtaining a Project ID and Name. Constraints N/A Range Project ID. Default Value N/A
service_id	Yes	String	Definition Service ID, which can be obtained from the response body during service creation or by obtaining services owned by the current user. The service_id field is the service ID. Constraints N/A Range Service ID. Default Value N/A

Request Parameters

**Table 2** Request header parameters
Parameter	Mandatory	Type	Description
X-Auth-Token	Yes	String	Definition User token. It can be obtained by calling the IAM API used to obtain a user token. The value of X-Subject-Token in the response header is the user token. For details about how to obtain the token, see Obtaining a User Token Through Password Authentication. Constraints N/A Range N/A Default Value N/A
Content-Type	Yes	String	Definition Message body type or format. Constraints N/A Range application/json application/json;charset=utf-8 Default Value N/A

**Table 3** Request body parameters
Parameter	Mandatory	Type	Description
id	No	String	Definition Deployment ID. Constraints N/A Range N/A Default Value N/A
name	Yes	String	Definition Deployment name. Constraints N/A Range N/A Default Value N/A
pool_id	No	String	Definition Resource pool ID. Services in a specified resource pool are queried. By default, no resource pool is filtered. You can obtain the value by querying the resource pool list. Constraints N/A Range N/A Default Value N/A
count	No	Integer	Definition Number of service instances in the deployment scenario. Constraints N/A Range [1, 128] Default Value N/A
system_log_dump_enable	No	Boolean	Definition Specifies whether to enable system log dump. Constraints This parameter is available only for NPU resource pools. Range N/A Default Value false
unit_configs	No	Array of UnitConfig objects	Definition Inference unit configuration. Constraints For single-node inference, the number of instance units is 1. For distributed inference, the number of instances can be configured based on the framework.
weight	Yes	Integer	Definition Weight percentage of the traffic allocated to the model. This parameter is mandatory only when the model is deployed as a real-time service. Constraints N/A Range [0,100] Default Value N/A
secret_type	No	String	Definition Secret type. You can select the secret type (dew or agency) to be used here. Constraints If the temporary agency credential is used, the following constraints must be met: CCE Container Storage (Everest) v2.4.204 or later has been installed in the cluster, the cluster version is v1.28 or later, and IAM5 has been enabled at the site. If the plugin version is insufficient or the cluster does not support temporary credentials, you need to mount the credentials through DEW. Range [dew: DEW secret.] (tag:hws,hws_hk,fcs) agency: temporary agency credential. Default Value N/A
secret_name	No	String	Definition Secret name. When using a DEW secret, you can select the secret to be used here. Constraints N/A
priority	No	Integer	Definition Service priority. Constraints If the service is in the Running state, the priority field is mandatory, and the value must be the same as the priority value of the original service. If the service is in the Stopped state, the priority field is optional. Range [1, 3] Default Value N/A
high_avail_switch	No	Boolean	Definition Specifies whether to enable HA. Once enabled, pods of different instances are evenly distributed to different nodes. (This parameter is about to be brought offline. Use the schedule_strategy field instead.) Constraints N/A Range true: HA is enabled. false: HA is disabled. Default Value true
schedule_strategy	No	String	Definition Scheduling policy. Constraints N/A Range HIGH_AVAILABILITY: HA scheduling HIGH_UTILIZATION: compact scheduling HIGH_PERFORMANCE: high-performance scheduling Default Value HIGH_AVAILABILITY
version	No	String	Definition Service version, which consists of digits and periods (.), for example, 1.0.1. Constraints N/A Range The value ranges from 1.0.0 to 99.99.99 and can contain at most eight characters. Default Value N/A
version_id	No	String	Definition Version ID, which can be obtained by querying the version list. Constraints N/A Range N/A Default Value N/A
description	No	String	Definition Service description. Constraints N/A Range The value can contain a maximum of 512 characters and cannot contain greater-than signs (>) or less-than signs (<). Default Value This parameter is left blank by default.
framework	No	String	Definition Service framework. Constraints Only the following enumerated values are supported: COMMON \| VLLM \| MINDIE. Range Only the following enumerated values are supported: COMMON \| VLLM \| MINDIE. Default Value COMMON.
running_count	No	Integer	Definition Number of service running instances in the deployment scenario. Constraints N/A Range [1, 128] Default Value N/A
deploy_type	No	String	Definition Deployment type. Range SINGLE: single-node single-PU MULTI: multi-node multi-PU
mirror_traffic_enable	No	Boolean	Definition Specifies whether to enable image traffic. Range N/A
mirror_traffic_weight	No	String	Definition Image traffic weight. Range 50
version_count	No	Integer	Definition Number of service versions. Range N/A
update_at	No	Long	Definition Update time, which is automatically generated. Range Millisecond-level timestamp, which is a 13-digit number.
model	No	ModelResource object	Definition Model configuration shared by all inference units. You can select a model and weight file to use with the image. This configuration takes effect for all inference units. Constraints N/A
advanced_config	No	AdvancedConfig object	Definition Advanced service deployment settings. Constraints N/A Range N/A Default Value N/A

**Table 4** UnitConfig
Parameter	Mandatory	Type	Description
id	No	String	Definition Instance unit ID. Constraints N/A Range N/A Default Value N/A
name	No	String	Definition Role name of the instance unit. Constraints The value can contain a maximum of 16 characters and must meet the regular expression ^[a-z0-9]([-a-z0-9][a-z0-9])?$. Default Value* N/A
role	No	String	Definition Instance unit role. Constraints N/A Range COMMON: other roles Default Value N/A
custom_spec	No	CustomResourceSpec object	Definition Custom resource specifications. Constraints N/A Example "custom_spec": { "arch": "x86", "cpu": 0.51, "memory": 1024.0 },
flavor	No	String	Definition Resource specifications. Select specifications based on service requirements. When specification is set to custom, the custom specifications are used. custom_spec specifies deployment specifications. Constraints N/A Range N/A Default Value N/A
flavor_display_name	No	String	Definition Display name of a resource specification. Constraints N/A Range N/A Default Value N/A
image	Yes	ImageInfo object	Definition Image configuration information, including the image path and image source. Constraints N/A
models	No	Array of ModelResource objects	Definition This parameter is discarded. You are advised to use files to configure models. Model configuration. You can select a model and weight file to use with the image. Constraints N/A
codes	No	Array of Code objects	Definition This parameter is discarded. You are advised to use files to configure code. Code configuration. You can select the OBS path where the code is stored. Constraints N/A
files	No	Array of FileInfo objects	Definition Model and code configuration. You can select the model and weight file to work with the image and the OBS path where the code is stored. Constraints N/A
dumps	No	Array of Dump objects	Definition Dump configuration. You can select the OBS bucket where the data is to be dumped. Constraints A maximum of 20 groups can be configured.
count	No	Integer	Definition Number of configuration instances. Constraints N/A Range N/A Default Value N/A
cmd	No	String	Definition Startup command. Constraints N/A Range N/A Default Value N/A
termination_grace	No	TerminationGrace object	Definition Graceful shutdown configuration. Constraints N/A
envs	No	Map<String,String>	Definition Environment variable. Constraints The length of a variable key cannot exceed 64 characters. The key can only contain letters, digits, underscores (_), hyphens (-), and periods (.), and cannot start with a digit. The value cannot contain HTML tags, including <^>.
readiness_health	No	Health object	Definition Readiness health check. Constraints N/A
startup_health	No	Health object	Definition Health checks are enabled. Constraints N/A
liveness_health	No	Health object	Definition Liveness health check. Range N/A
port	No	Integer	Definition Port. Constraints N/A Range [1, 65535] Default Value N/A
recovery	No	String	Definition Auto-rebuild policy. When enabled, the platform will automatically rebuild pods according to the policy if they restart due to deployment configuration changes or hardware failures. If disabled, the platform will not intervene. Constraints N/A Range Instance: Deployment replica rebuilding. Restarts the entire deployment when a fault occurs. Role: Unit rebuilding. Restarts all pods within a deployment unit if any pod in that unit fails. Pod: Pod rebuilding. Restarts the faulty pod if it fails. Default Value N/A
npu_reset_enable	No	Boolean	Definition Specifies whether to enable the recovery policy. Constraints N/A Range true: The recovery policy is enabled. false: The recovery policy is disabled. Default Value N/A
group_count	No	Integer	Definition Number of replicas in a unit. This parameter is invalid when deploy_type is set to SINGLE or workload_type is set to DEPLOYMENT. Constraints N/A Range [1, 100] or left empty. Default Value 1
affinity	No	Affinity object	Definition Node affinity scheduling. Constraints N/A
security_config	No	ServiceSecurityConfig object	Definition Container user ID/user group ID. Constraints N/A
pool_resource_flavor	No	String	Definition Node pool resource specifications. Constraints The value can contain only letters, digits, periods (.), hyphens (-), and underscores (_). Range The value can contain a maximum of 128 characters. Default Value N/A

**Table 5** CustomResourceSpec
Parameter	Mandatory	Type	Description
gpu	No	Float	Definition Number of GPUs. Constraints N/A Range The value can be a decimal. It cannot be smaller than 0, with the third decimal place is rounded off. Default Value N/A
memory	No	Integer	Definition Memory size, in MB. Constraints N/A Range Only integers are supported. Default Value N/A
cpu	No	Float	Definition CPU cores. Constraints N/A Range The value can be a decimal. It cannot be smaller than 0.01, with the third decimal place is rounded off. Default Value N/A
ascend	No	Integer	Definition Number of Ascend chips. Constraints N/A Range N/A Default Value N/A
arch	No	String	Definition Architecture type. Constraints N/A Range x86/arm64. Default Value N/A

**Table 6** ImageInfo
Parameter	Mandatory	Type	Description
id	No	String	Definition Image ID. Constraints N/A Range N/A Default Value N/A
source	Yes	String	Definition Image type, which indicates the image source. Constraints N/A Range SWR: SoftWare Repository for Container (SWR) [IMAGE: [general image].] Default Value N/A
swr_path	Yes	String	Definition Image path. The address is different when the source value is different. Constraints N/A Range N/A Default Value N/A
category	No	String	Definition Flavors supported by the image. Constraints N/A Range GPU: graphics processing unit. CPU: central processing unit. ASCEND: Ascend chip. Default Value CPU

**Table 7** ModelResource
Parameter	Mandatory	Type	Description
source	Yes	String	Definition Code source type. Constraints N/A Range The value is case-insensitive. OBS: Object Storage Service OBSFS: OBS file system API EFS: Scalable File Service LOCAL: local storage directory to which the host machine is mounted. Default Value N/A
address	No	String	Definition Code source address, which complies with the format of different storage systems. Constraints N/A Range N/A Default Value N/A
mount_path	Yes	String	Definition Path mounted to the container. The value must start with a slash (/) and can contain hyphens (-), backslashes (), underscores (), periods (.), letters, and digits. Constraints N/A Range The value must start and end with a slash (/) and can contain at most 255 characters. Only letters, digits, hyphens (-), and underscores () are allowed. Default Value N/A
host_cache	No	Boolean	Definition Specifies whether the model can be cached locally. This function is disabled by default. Constraints N/A Range true: supported. false: not supported. Default Value false
efs_sub_path	No	String	Definition When the storage type is EFS, subdirectories can be configured. Constraints N/A Range N/A Default Value N/A
read_only	No	Boolean	Definition Specifies whether the mount permission is read-only. Constraints N/A Range true: read only false: non-read-only Default Value N/A
os_warm_up	No	Boolean	Definition OS warmup. Constraints N/A Range true: Warmup enabled. false: Warmup disabled. Default Value N/A
source_name	No	String	Definition Warmup name. Constraints This parameter is mandatory when os_warm_up is set to true. Range The value can contain at most 64 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A
asset_id	No	String	Definition Preset asset ID. Constraints This parameter is mandatory when preset assets are used. Range The value can contain at most 64 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A

**Table 8** Code
Parameter	Mandatory	Type	Description
source	Yes	String	Definition Code source type. Constraints N/A Range OBS: Object Storage Service OBSFS: OBS file system API EFS: Scalable File Service Default Value N/A
address	No	String	Definition Code source address, which complies with the format of different storage systems. Constraints N/A Range N/A Default Value N/A
source_id	No	String	Definition Code source ID. Either this parameter or address must be specified. The SFS Turbo ID can be input only when source is set to EFS. Constraints N/A Range N/A Default Value N/A
mount_path	Yes	String	Definition Path mounted to the container. Constraints N/A Range The value must start and end with a slash (/) and can contain at most 255 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A
efs_sub_path	No	String	Definition EFS subpath. Constraints N/A Range N/A Default Value N/A
read_only	No	Boolean	Definition Specifies whether the mount permission is read-only. Constraints N/A Range true: read only false: non-read-only Default Value N/A

**Table 9** FileInfo
Parameter	Mandatory	Type	Description
source	Yes	String	Definition Code source type. Constraints N/A Range The value is case-insensitive. OBS: Object Storage Service OBSFS: OBS file system API EFS: Scalable File Service LOCAL: local storage directory to which the host machine is mounted. Default Value N/A
address	No	String	Definition Code source address, which complies with the format of different storage systems. Constraints N/A Range N/A Default Value N/A
mount_path	Yes	String	Definition Path mounted to the container. Constraints N/A Range The value must start and end with a slash (/) and can contain at most 255 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A
host_cache	No	Boolean	Definition Specifies whether the model can be cached locally. This function is disabled by default. Constraints N/A Range true: supported. false: not supported. Default Value false
efs_sub_path	No	String	Definition When the storage type is EFS, subdirectories can be configured. Constraints N/A Range N/A Default Value N/A
read_only	No	Boolean	Definition Specifies whether the mount permission is read-only. Constraints N/A Range true: read only false: non-read-only Default Value N/A
os_warm_up	No	Boolean	Definition OS warmup. Constraints N/A Range true: Warmup enabled. false: Warmup disabled. Default Value N/A
source_name	No	String	Definition Warmup name. Constraints This parameter is mandatory when os_warm_up is set to true. Range The value can contain at most 64 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A

**Table 10** Dump
Parameter	Mandatory	Type	Description
source	Yes	String	Definition Source type of the dump mount directory. Constraints N/A Range OBS: Object Storage Service OBSFS: OBS file system API Default Value N/A
address	No	String	Definition Source address of the dump mount directory. The value can be an HTTPS or OBS address. Constraints N/A Range N/A Default Value N/A
mount_path	Yes	String	Definition Path mounted to the container. The value must start with a slash (/) and can contain hyphens (-), backslashes (), underscores (_), periods (.), letters, and digits. Constraints N/A Range N/A Default Value N/A

**Table 11** TerminationGrace
Parameter	Mandatory	Type	Description
pre_stop_cmd	No	String	Definition: The shutdown command is triggered when the container receives a stop signal, but it must be completed within the grace period or the shutdown times out. If this happens, the container will be forcefully stopped. You can use this command to perform operations such as closing database connections, releasing file handles, and stopping child processes. Constraints The value can contain up to 255 characters. Range Protocol: http or https Port: 1 to 65535 Address: Only letters, digits, periods (.), hyphens (-), underscores (_), and slashes (/) are allowed. The value cannot start with a slash (/). Default Value N/A
termination_grace_period_seconds	No	Integer	Definition This parameter indicates the maximum length of time that can pass between when a Pod receives a stop signal to when it is forcefully stopped. It is used for the Pod to perform cleanup operations (such as closing connections, releasing resources, and saving states). Constraints The value can contain up to 255 characters. Range Protocol: http or https Port: 1 to 65535 Address: Only letters, digits, periods (.), hyphens (-), underscores (_), and slashes (/) are allowed. The value cannot start with a slash (/). Default Value N/A

**Table 12** Health
Parameter	Mandatory	Type	Description
check_method	No	String	Definition Health check method, which can be HTTP or EXEC (commands). Constraints N/A Range HTTP: Hypertext Transfer Protocol EXEC: commands Default Value During creation, if check_method is not specified, the default value is check_method. During update, if check_method is not specified, an error will be reported.
cmd	No	String	Definition Command line mandatory when the health check method is EXEC. Constraints The value can contain 0 to 1,024 characters and cannot contain the following characters: #~^$\|%&<>()'"[]{} Range* N/A Default Value N/A
url	No	String	Definition Request address mandatory when the health check mode is HTTP. Constraints The value can contain 0 to 1,024 characters. The first character must be a slash (/), and the subsequent characters can be letters, digits, hyphens (-), underscores (_), slashes (/), and colons (:). Range N/A Default Value N/A
protocol	No	String	Definition Connection protocol. The default value is HTTP. Constraints N/A Range HTTPS: Hypertext Transfer Protocol Secure HTTP: Hypertext Transfer Protocol WSS: WebSocket Secure WS: WebSocket Default Value N/A
initial_delay_seconds	Yes	Integer	Definition Waiting time before the first detection. The default value is 30 and the minimum value is 1. Constraints N/A Range N/A Default Value 30
timeout_seconds	Yes	Integer	Definition Timeout interval of the detection. The default value is 30 seconds, and the minimum value is 1 second. Constraints N/A Range The minimum value is 1 second. Default Value 30s
period_seconds	Yes	Integer	Definition Interval at which the health check is performed. The default value is 10 seconds, and the minimum value is 1 second. Constraints N/A Range The minimum value is 1 second. Default Value 10s
failure_threshold	Yes	Integer	Definition The minimum number of consecutive detection failures required after a successful detection. Detection is considered failed only when this threshold is reached. The default value is 3. The minimum value is 1. Constraints N/A Range The minimum value is 1. Default Value 3

**Table 13** Affinity
Parameter	Mandatory	Type	Description
affinity_type	Yes	String	Definition Node affinity type. Constraints N/A Range AFFINITY: affinity ANTI_AFFINITY: anti-affinity Default Value N/A
required	Yes	Boolean	Definition Specifies whether to set strong affinity. Constraints N/A Range true: Strong affinity is set. false: Strong affinity is not set. Default Value N/A
selection_mode	Yes	String	Definition Node selection mode. Constraints N/A Range IP Default Value N/A
targets	Yes	Map<String,String>	Definition List selected using the preceding method, whose length cannot exceed 20. Constraints N/A

**Table 14** ServiceSecurityConfig
Parameter	Mandatory	Type	Description
user_id	No	Long	Definition user_id set during service container startup. This parameter can be left empty by default. Range [1, 60000]
group_id	No	Long	Definition group_id set during service container startup. This parameter can be left empty by default. Range [1, 60000]

**Table 15** AdvancedConfig
Parameter	Mandatory	Type	Description
deploy_timeout_minutes	No	String	Definition Deployment timeout.
upgrade_config	Yes	UpgradeConfig object	Definition Rolling upgrade configuration.
service_secret	No	ServiceSecret object	Definition Service secret.
dynamic_routing_enable	No	Boolean	Definition Intelligent routing switch.
strategy	No	String	Definition Intelligent routing policy.
ems_enable	No	Boolean	Definition EMS acceleration switch.
metric_api_scheme	No	String	Definition Intelligent routing metric collection scheme.
metric_api_port	No	String	Definition Intelligent routing metric collection port.
metric_api_path	No	String	Definition Intelligent routing metric collection URL.
custom_metrics_path	No	String	Definition Custom metric collection URL.
port	Yes	Integer	Definition Container port.
protocol	Yes	String	Definition Container request protocol. When WSS or WS is selected, the service API is upgraded to WebSocket. WebSocket cannot be enabled together with Traffic Limit. Range HTTP: HTTP protocol HTTPS: HTTPS protocol WSS: WebSocket Secure protocol WS: WebSocket protocol TCP: Transmission Control Protocol NA: No protocol used

**Table 16** UpgradeConfig
Parameter	Mandatory	Type	Description
type	No	String	Definition Upgrade type. Constraints N/A Range ROLLING: rolling upgrade (default value) Default Value N/A
rolling_update	No	RollingUpdate object	Definition Rolling update configuration. Constraints N/A

**Table 17** RollingUpdate
Parameter	Mandatory	Type	Description
max_surge	No	String	Definition Maximum number of pods that can be started during rolling update. Constraints A percentage-type string. Range 1/ %to 100% Default Value 1%.
max_unavailable	No	String	Definition Maximum number of pods that can be deleted during rolling update. Constraints A percentage-type string. Range 1/ %to 100% Default Value 1%.

**Table 18** ServiceSecret
Parameter	Mandatory	Type	Description
secret_enable	No	Boolean	Definition Specifies whether to enable the key. Constraints N/A Range true: The secret is enabled. false: The secret is disabled. Default Value false
secret_type	No	String	Definition Secret type. Constraints N/A Range custom: custom secret. [dew: DEW secret.] (tag:hws,hws_hk,fcs) Default Value N/A
secret_volumes	No	Array of SecretVolume objects	Definition Secret volume mounting. Constraints Maximum: 30
group_enable	No	Boolean	Definition Specifies whether to enable the image user group. Constraints N/A Range true: The user group of the image is enabled. false: The user group of the image is not enabled. Default Value false
group_id	No	Long	Definition User group ID of the image. Constraints N/A Range 1000 to 4294967294 Default Value N/A

**Table 19** SecretVolume
Parameter	Mandatory	Type	Description
secret_name	No	String	Definition Secret name. Constraints N/A Range N/A Default Value N/A
secret_key	No	String	Definition Secret key. Constraints A string of 1 to 63 characters is matched. Only letters, digits, dots (.), underscores (_), and hyphens (-) are allowed. The string cannot start with two consecutive dots (..). Range N/A Default Value N/A
secret_value	No	String	Definition Secret value. Constraints The value is a Base64-encoded secret value and contains 1 to 32,768 characters. Range N/A Default Value N/A
mount_path	Yes	String	Definition Mount path. Constraints N/A Range The value must start and end with a slash (/) and can contain at most 255 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A

Response Parameters

Status code: 200

**Table 20** Response body parameters
Parameter	Type	Description
id	String	Definition Deployment ID. Range N/A
name	String	Definition Deployment name. Range N/A
pool_id	String	Definition Resource pool ID. Services in a specified resource pool are queried. By default, no resource pool is filtered. You can obtain the value by querying the resource pool list. Range N/A
count	Integer	Definition Number of service instances in the deployment scenario. Constraints N/A Range [1, 128] Default Value N/A
system_log_dump_enable	Boolean	Definition Specifies whether to enable system log dump. Constraints This parameter is available only for NPU resource pools. Range N/A Default Value false
unit_configs	Array of UnitConfigResponse objects	Definition Inference unit configuration.
weight	Integer	Definition Weight percentage of the traffic allocated to the model. This parameter is mandatory only when the model is deployed as a real-time service. Range [0,100]
traffic_ratio	String	Definition Traffic ratio, that is, the ratio of the expected user traffic to the total traffic of a single deployment instance. The value is calculated based on the traffic weight configuration and deployment status. Range 0.00/ %to 100.00%
secret_type	String	Definition Secret type. You can select the secret type (dew or agency) to be used here. Constraints N/A Range [dew: DEW secret.] (tag:hws,hws_hk,fcs) agency: temporary agency credential. Default Value N/A
secret_name	String	Definition Secret name. When using a DEW secret, you can select the secret to be used here. Constraints N/A
priority	Integer	Definition Service priority. Constraints N/A Range [1, 3] Default Value N/A
high_avail_switch	Boolean	Definition Specifies whether to enable HA. Once enabled, pods of different instances are evenly distributed to different nodes. (This parameter is about to be brought offline. Use the schedule_strategy field instead.) Range true: HA is enabled. false: HA is disabled.
framework	String	Definition Algorithm framework. Range COMMON: common real-time service.
version	String	Definition Service version, which consists of digits and periods (.), for example, 1.0.1. Constraints N/A Range The value ranges from 1.0.0 to 99.99.99 and can contain at most eight characters. Default Value N/A
version_id	String	Definition Version ID, which can be obtained by querying the version list. Constraints N/A Range N/A Default Value N/A
status	String	Definition Service status. Range DEPLOYING FAILED STOPPED RUNNING DELETING STOPPING CONCERNING: There is an alarm. DELETED RESTARTING UPGRADING ERROR: abnormal INTERRUPTING
running_count	Integer	Definition Number of service running instances in the deployment scenario. Constraints N/A Range [1, 128] Default Value N/A
deploy_type	String	Definition Deployment type. Range SINGLE: single-node single-PU MULTI: multi-node multi-PU
mirror_traffic_enable	Boolean	Definition Specifies whether to enable image traffic. Range N/A
mirror_traffic_weight	String	Definition Image traffic weight. Range 50
version_count	Integer	Definition Number of service versions. Range N/A
workload_type	String	Definition Workload type. Range N/A
update_at	Long	Definition Update time, which is automatically generated. Range Millisecond-level timestamp, which is a 13-digit number.
lts_state	String	Definition Status of the interconnection between the deployment and LTS. Range ON: enabled OFF: disabled
infer_name	String	Definition Deployment ID.
model	InferModelResponse object	Definition Model configuration. You can select a model and weight file to use with the image. Constraints N/A
advanced_config	AdvancedConfig object	Definition Advanced deployment settings. Constraints N/A
description	String	Definition Deployment description.
create_at	String	Definition Creation time, which is automatically generated. Range Millisecond-level timestamp, which is a 13-digit number, for example, 1609459200000.
schedule_strategy	String	Definition Scheduling policy. Range HIGH_AVAILABILITY: HA scheduling HIGH_UTILIZATION: compact scheduling HIGH_PERFORMANCE: high-performance scheduling

**Table 21** UnitConfigResponse
Parameter	Type	Description
id	String	Definition Instance unit ID. Range N/A
name	String	Definition Instance unit name. Range N/A
role	String	Definition Instance unit role. Range COMMON: other roles
custom_spec	CustomResourceSpec object	Definition Custom resource specifications.
flavor	String	Definition Resource specifications. Select specifications based on service requirements. When specification is set to custom, the custom specifications are used. custom_spec specifies deployment specifications. Range N/A
image	ImageInfoResponse object	Definition Image configuration information, including the image path and image source.
models	Array of InferModelResponse objects	Definition Model configuration. You can select a model and weight file to use with the image.
files	Array of FileResponse objects	Definition Model and code configuration. You can select the model and weight file to work with the image and the OBS path where the code is stored.
codes	Array of CodeResponse objects	Definition Code configuration. You can select the OBS path where the code is stored.
dumps	Array of DumpResponse objects	Definition Dump configuration. You can select the OBS path where the data is to be dumped.
count	Integer	Definition Number of configuration instances. Range N/A
group_count	Integer	Definition Number of replicas in a unit. This parameter is invalid when deploy_type is set to SINGLE or workload_type is set to DEPLOYMENT. Range [1, 100] or left empty. Default Value 1
cmd	String	Definition Startup command. Range N/A
envs	Map<String,String>	Definition Environment variable.
readiness_health	HealthResponse object	Definition Readiness health check.
startup_health	HealthResponse object	Definition Health checks are enabled.
liveness_health	HealthResponse object	Definition Liveness health check.
port	Integer	Definition Port. Range [1, 65535]
recovery	String	Definition Auto-rebuild policy. When enabled, the platform will automatically rebuild pods according to the policy if they restart due to deployment configuration changes or hardware failures. If disabled, the platform will not intervene. Range Instance: Deployment replica rebuilding. Restarts the entire deployment when a fault occurs. Role: Unit rebuilding. Restarts all pods within a deployment unit if any pod in that unit fails. Pod: Pod rebuilding. Restarts the faulty pod if it fails.
npu_reset_enable	Boolean	Definition Specifies whether to enable the recovery policy. Range true: The recovery policy is enabled. false: The recovery policy is disabled.
affinity	AffinityResponse object	Definition Node affinity scheduling.
flavor_display_name	String	Definition Specification display name. This field is returned only for services deployed using the allocated specifications. Range N/A
termination_grace	TerminationGrace object	Definition Once enabled, you can configure shutdown timeouts and commands. This prevents in-progress requests from being forcibly interrupted, thereby enhancing the availability and stability of the system. Constraints The value can contain up to 255 characters. Range Protocol: http or https Port: 1 to 65535 Address: Only letters, digits, periods (.), hyphens (-), underscores (_), and slashes (/) are allowed. The value cannot start with a slash (/). Default Value N/A
security_config	ServiceSecurityConfig object	Definition Settings for starting the service container. Range N/A
pool_resource_flavor	String	Definition Node pool resource specifications. Constraints The value can contain only letters, digits, periods (.), hyphens (-), and underscores (_). Range The value can contain a maximum of 128 characters. Default Value N/A

**Table 22** CustomResourceSpec
Parameter	Type	Description
gpu	Float	Definition Number of GPUs. Constraints N/A Range The value can be a decimal. It cannot be smaller than 0, with the third decimal place is rounded off. Default Value N/A
memory	Integer	Definition Memory size, in MB. Constraints N/A Range Only integers are supported. Default Value N/A
cpu	Float	Definition CPU cores. Constraints N/A Range The value can be a decimal. It cannot be smaller than 0.01, with the third decimal place is rounded off. Default Value N/A
ascend	Integer	Definition Number of Ascend chips. Constraints N/A Range N/A Default Value N/A
arch	String	Definition Architecture type. Constraints N/A Range x86/arm64. Default Value N/A

**Table 23** ImageInfoResponse
Parameter	Type	Description
id	String	Definition Image ID. Range N/A
source	String	Definition Image type, which indicates the image source. Range SWR: SoftWare Repository for Container (SWR)
swr_path	String	Definition Image path. The address is different when the source value is different. Range N/A
category	String	Definition Flavors supported by the image. Range GPU: graphics processing unit. CPU: central processing unit. ASCEND: Ascend chip.

**Table 24** InferModelResponse
Parameter	Type	Description
source	String	Definition Code source type. Constraints N/A Range The value is case-insensitive. OBS: Object Storage Service OBSFS: OBS file system API EFS: Scalable File Service LOCAL: local storage directory to which the host machine is mounted. Default Value N/A
address	String	Definition Code source address, which complies with the format of different storage systems. Constraints N/A Range N/A Default Value N/A
source_id	String	Definition Source ID. Constraints N/A Range N/A Default Value N/A
mount_path	String	Definition Path mounted to the container. The value must start with a slash (/) and can contain hyphens (-), backslashes (), underscores (), periods (.), letters, and digits. Constraints N/A Range The value must start and end with a slash (/) and can contain at most 255 characters. Only letters, digits, hyphens (-), and underscores () are allowed. Default Value N/A
host_cache	Boolean	Definition Specifies whether the model can be cached locally. This function is disabled by default. Constraints N/A Range true: supported. false: not supported. Default Value false
efs_sub_path	String	Definition When the storage type is EFS, subdirectories can be configured. Constraints N/A Range N/A Default Value N/A
read_only	Boolean	Definition Specifies whether the mount permission is read-only. Constraints N/A Range true: read only false: non-read-only Default Value N/A
os_warm_up	Boolean	Definition OS warmup. Constraints N/A Range true: Warmup enabled. false: Warmup disabled. Default Value N/A
source_name	String	Definition Warmup name. Constraints This parameter is mandatory when os_warm_up is set to true. Range The value can contain at most 64 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A
asset_id	String	Definition Preset asset ID. Constraints This parameter is mandatory when preset assets are used. Range The value can contain at most 64 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A

**Table 25** FileResponse
Parameter	Type	Description
source	String	Definition Code source type. Range OBS: Object Storage Service OBSFS: OBS file system API EFS: Scalable File Service LOCAL: local storage directory to which the host machine is mounted.
address	String	Definition Code source address, which complies with the format of different storage systems. Range N/A
mount_path	String	Definition Path mounted to the container. Constraints N/A Range The value must start and end with a slash (/) and can contain at most 255 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A
host_cache	Boolean	Definition Specifies whether the model can be cached locally. This function is disabled by default. Range true: supported. false: not supported.
efs_sub_path	String	Definition When the storage type is EFS, subdirectories can be configured. Range N/A
read_only	Boolean	Definition Specifies whether the mount permission is read-only. Range true: read only false: non-read-only
os_warm_up	Boolean	Definition OS warmup. Range true: Warmup enabled. false: Warmup disabled.
source_name	String	Definition Warmup name. Constraints This parameter is mandatory when os_warm_up is set to true. Range The value can contain at most 64 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A

**Table 26** CodeResponse
Parameter	Type	Description
source	String	Definition Code source type. Range OBS: Object Storage Service OBSFS: OBS file system API EFS: Scalable File Service
address	String	Definition Code source address, which complies with the format of different storage systems. Range N/A
source_id	String	Definition Code source ID. Either this parameter or address must be specified. The SFS Turbo ID can be input only when source is set to EFS. Range N/A
mount_path	String	Definition Path mounted to the container. Constraints N/A Range The value must start and end with a slash (/) and can contain at most 255 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A
efs_sub_path	String	Definition EFS subpath. Range N/A
read_only	Boolean	Definition Specifies whether the mount permission is read-only. Range true: read only false: non-read-only

**Table 27** DumpResponse
Parameter	Type	Description
source	String	Definition Dump source type. Range OBS: Object Storage Service OBSFS: OBS file system API
address	String	Definition Dump source address, which complies with the format of different storage systems. Range N/A
mount_path	String	Definition Path mounted to the container. The value must start with a slash (/) and can contain hyphens (-), backslashes (), underscores (_), periods (.), letters, and digits. Range N/A
type	String	Definition Transfer type. Range DUMP: user-defined dump DUMP_SYS: system dump

**Table 28** HealthResponse
Parameter	Type	Description
check_method	String	Definition Health check method, which can be HTTP or EXEC (commands). Constraints N/A Range HTTP: Hypertext Transfer Protocol EXEC: commands Default Value N/A
cmd	String	Definition Command line when the health check method is EXEC. Constraints The value can contain 0 to 1,024 characters and cannot contain the following characters: #~^$\|%&<>()'"[]{} Range* N/A Default Value N/A
url	String	Definition Request address when the health check mode is HTTP. Constraints The value can contain 0 to 1,024 characters. The first character must be a slash (/), and the subsequent characters can be letters, digits, hyphens (-), underscores (_), slashes (/), and colons (:). Range N/A Default Value N/A
protocol	String	Definition Connection protocol. The default value is HTTP. Constraints N/A Range HTTPS: Hypertext Transfer Protocol Secure HTTP: Hypertext Transfer Protocol WSS: WebSocket Secure WS: WebSocket Default Value N/A
initial_delay_seconds	Integer	Definition Waiting time before the first detection. The default value is 30 and the minimum value is 1. Constraints N/A Range N/A Default Value 30
timeout_seconds	Integer	Definition Timeout interval of the detection. The default value is 30 seconds, and the minimum value is 1 second. Constraints N/A Range The minimum value is 1 second. Default Value 30s
period_seconds	Integer	Definition Interval at which the health check is performed. The default value is 10 seconds, and the minimum value is 1 second. Constraints N/A Range The minimum value is 1 second. Default Value 10s
failure_threshold	Integer	Definition The minimum number of consecutive detection failures required after a successful detection. Detection is considered failed only when this threshold is reached. The default value is 3. The minimum value is 1. Constraints N/A Range The minimum value is 1. Default Value 3

**Table 29** AffinityResponse
Parameter	Type	Description
affinity_type	String	Definition Node affinity type. Range AFFINITY: affinity ANTI_AFFINITY: anti-affinity
required	Boolean	Definition Specifies whether to set strong affinity. Range true: Strong affinity is set. false: Strong affinity is not set.
selection_mode	String	Definition Node selection mode. Range IP
targets	Map<String,String>	Definition List selected using the preceding method, whose length cannot exceed 20.

**Table 30** TerminationGrace
Parameter	Type	Description
pre_stop_cmd	String	Definition: The shutdown command is triggered when the container receives a stop signal, but it must be completed within the grace period or the shutdown times out. If this happens, the container will be forcefully stopped. You can use this command to perform operations such as closing database connections, releasing file handles, and stopping child processes. Constraints The value can contain up to 255 characters. Range Protocol: http or https Port: 1 to 65535 Address: Only letters, digits, periods (.), hyphens (-), underscores (_), and slashes (/) are allowed. The value cannot start with a slash (/). Default Value N/A
termination_grace_period_seconds	Integer	Definition This parameter indicates the maximum length of time that can pass between when a Pod receives a stop signal to when it is forcefully stopped. It is used for the Pod to perform cleanup operations (such as closing connections, releasing resources, and saving states). Constraints The value can contain up to 255 characters. Range Protocol: http or https Port: 1 to 65535 Address: Only letters, digits, periods (.), hyphens (-), underscores (_), and slashes (/) are allowed. The value cannot start with a slash (/). Default Value N/A

**Table 31** ServiceSecurityConfig
Parameter	Type	Description
user_id	Long	Definition user_id set during service container startup. This parameter can be left empty by default. Range [1, 60000]
group_id	Long	Definition group_id set during service container startup. This parameter can be left empty by default. Range [1, 60000]

**Table 32** AdvancedConfig
Parameter	Type	Description
deploy_timeout_minutes	String	Definition Deployment timeout.
upgrade_config	UpgradeConfig object	Definition Rolling upgrade configuration.
service_secret	ServiceSecret object	Definition Service secret.
dynamic_routing_enable	Boolean	Definition Intelligent routing switch.
strategy	String	Definition Intelligent routing policy.
ems_enable	Boolean	Definition EMS acceleration switch.
metric_api_scheme	String	Definition Intelligent routing metric collection scheme.
metric_api_port	String	Definition Intelligent routing metric collection port.
metric_api_path	String	Definition Intelligent routing metric collection URL.
custom_metrics_path	String	Definition Custom metric collection URL.
port	Integer	Definition Container port.
protocol	String	Definition Container request protocol. When WSS or WS is selected, the service API is upgraded to WebSocket. WebSocket cannot be enabled together with Traffic Limit. Range HTTP: HTTP protocol HTTPS: HTTPS protocol WSS: WebSocket Secure protocol WS: WebSocket protocol TCP: Transmission Control Protocol NA: No protocol used

**Table 33** UpgradeConfig
Parameter	Type	Description
type	String	Definition Upgrade type. Constraints N/A Range ROLLING: rolling upgrade (default value) Default Value N/A
rolling_update	RollingUpdate object	Definition Rolling update configuration. Constraints N/A

**Table 34** RollingUpdate
Parameter	Type	Description
max_surge	String	Definition Maximum number of pods that can be started during rolling update. Constraints A percentage-type string. Range 1/ %to 100% Default Value 1%.
max_unavailable	String	Definition Maximum number of pods that can be deleted during rolling update. Constraints A percentage-type string. Range 1/ %to 100% Default Value 1%.

**Table 35** ServiceSecret
Parameter	Type	Description
secret_enable	Boolean	Definition Specifies whether to enable the key. Constraints N/A Range true: The secret is enabled. false: The secret is disabled. Default Value false
secret_type	String	Definition Secret type. Constraints N/A Range custom: custom secret. [dew: DEW secret.] (tag:hws,hws_hk,fcs) Default Value N/A
secret_volumes	Array of SecretVolume objects	Definition Secret volume mounting. Constraints Maximum: 30
group_enable	Boolean	Definition Specifies whether to enable the image user group. Constraints N/A Range true: The user group of the image is enabled. false: The user group of the image is not enabled. Default Value false
group_id	Long	Definition User group ID of the image. Constraints N/A Range 1000 to 4294967294 Default Value N/A

**Table 36** SecretVolume
Parameter	Type	Description
secret_name	String	Definition Secret name. Constraints N/A Range N/A Default Value N/A
secret_key	String	Definition Secret key. Constraints A string of 1 to 63 characters is matched. Only letters, digits, dots (.), underscores (_), and hyphens (-) are allowed. The string cannot start with two consecutive dots (..). Range N/A Default Value N/A
secret_value	String	Definition Secret value. Constraints The value is a Base64-encoded secret value and contains 1 to 32,768 characters. Range N/A Default Value N/A
mount_path	String	Definition Mount path. Constraints N/A Range The value must start and end with a slash (/) and can contain at most 255 characters. Only letters, digits, hyphens (-), and underscores (_) are allowed. Default Value N/A

Example Requests

Create a real-time inference service.

POST https://{endpoint}/v2/{project_id}/services/{service_id}/deployments

{
  "description" : null,
  "name" : "deployment-example",
  "weight" : 100,
  "pool_id" : "pool-example",
  "framework" : "COMMON",
  "count" : 1,
  "advanced_config" : {
    "upgrade_config" : {
      "rolling_update" : {
        "max_surge" : "1%",
        "max_unavailable" : "1%"
      },
      "type" : "ROLLING"
    },
    "port" : 0,
    "protocol" : "HTTPS"
  }
}

Example Responses

Status code: 200

Creating a real-time inference service succeeded.

{
  "count" : 1,
  "framework" : "COMMON",
  "id" : "8a927efb-43f6-4a0b-8222-a1b87d2d2fa8",
  "name" : "deployment-example",
  "description" : "infer-description",
  "pool_id" : "pool-xinfer-1216-dev-04f258c84780d5a52f3bc00dc15aa5e7",
  "priority" : 1,
  "unit_configs" : [ {
    "codes" : [ ],
    "count" : 1,
    "custom_spec" : {
      "cpu" : 0.1,
      "memory" : 50
    },
    "envs" : {
      "additionalProp1" : "string",
      "additionalProp2" : "string",
      "a" : "1"
    },
    "id" : "8a0e4ab7970bc24d01970bcd7f460003",
    "image" : {
      "category" : "CPU",
      "id" : "bc84b0e49e910cd7918b1dfaeaa478f9c7e5242c6733525ca88304f026fa24e4",
      "source" : "SWR",
      "swr_path" : "swr.cn-north-7.myhuaweicloud.com/example/helloworld-example:0.0.1"
    },
    "npu_reset_enable" : false,
    "port" : 65535,
    "role" : "COMMON"
  } ],
  "weight" : 100,
  "version" : "0.0.0",
  "status" : "DEPLOYING"
}