Reference documentation and code samples for the Google Cloud Gke Recommender V1 Client class ModelServerInfo.
Model server information gives. Valid model server info combinations can be found using GkeInferenceQuickstart.FetchProfiles.
Generated from protobuf message google.cloud.gkerecommender.v1.ModelServerInfo
Namespace
Google \ Cloud \ GkeRecommender \ V1Methods
__construct
Constructor.
| Parameters | |
|---|---|
| Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ model |
string
Required. The model. Open-source models follow the Huggingface Hub |
↳ model_server |
string
Required. The model server. Open-source model servers use simplified, lowercase names (e.g., |
↳ model_server_version |
string
Optional. The model server version. Use GkeInferenceQuickstart.FetchModelServerVersions to find available versions. If not provided, the latest available version is used. |
getModel
Required. The model. Open-source models follow the Huggingface Hub
owner/model_name format. Use
GkeInferenceQuickstart.FetchModels
to find available models.
| Returns | |
|---|---|
| Type | Description |
string |
|
setModel
Required. The model. Open-source models follow the Huggingface Hub
owner/model_name format. Use
GkeInferenceQuickstart.FetchModels
to find available models.
| Parameter | |
|---|---|
| Name | Description |
var |
string
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getModelServer
Required. The model server. Open-source model servers use simplified,
lowercase names (e.g., vllm). Use
GkeInferenceQuickstart.FetchModelServers
to find available servers.
| Returns | |
|---|---|
| Type | Description |
string |
|
setModelServer
Required. The model server. Open-source model servers use simplified,
lowercase names (e.g., vllm). Use
GkeInferenceQuickstart.FetchModelServers
to find available servers.
| Parameter | |
|---|---|
| Name | Description |
var |
string
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getModelServerVersion
Optional. The model server version. Use GkeInferenceQuickstart.FetchModelServerVersions to find available versions. If not provided, the latest available version is used.
| Returns | |
|---|---|
| Type | Description |
string |
|
setModelServerVersion
Optional. The model server version. Use GkeInferenceQuickstart.FetchModelServerVersions to find available versions. If not provided, the latest available version is used.
| Parameter | |
|---|---|
| Name | Description |
var |
string
|
| Returns | |
|---|---|
| Type | Description |
$this |
|