Reference documentation and code samples for the GKE Recommender V1 API class Google::Cloud::GkeRecommender::V1::ModelServerInfo.
Model server information gives. Valid model server info combinations can be found using GkeInferenceQuickstart.FetchProfiles.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#model
def model() -> ::String
Returns
-
(::String) — Required. The model. Open-source models follow the Huggingface Hub
owner/model_name
format. Use GkeInferenceQuickstart.FetchModels to find available models.
#model=
def model=(value) -> ::String
Parameter
-
value (::String) — Required. The model. Open-source models follow the Huggingface Hub
owner/model_name
format. Use GkeInferenceQuickstart.FetchModels to find available models.
Returns
-
(::String) — Required. The model. Open-source models follow the Huggingface Hub
owner/model_name
format. Use GkeInferenceQuickstart.FetchModels to find available models.
#model_server
def model_server() -> ::String
Returns
-
(::String) — Required. The model server. Open-source model servers use simplified,
lowercase names (e.g.,
vllm
). Use GkeInferenceQuickstart.FetchModelServers to find available servers.
#model_server=
def model_server=(value) -> ::String
Parameter
-
value (::String) — Required. The model server. Open-source model servers use simplified,
lowercase names (e.g.,
vllm
). Use GkeInferenceQuickstart.FetchModelServers to find available servers.
Returns
-
(::String) — Required. The model server. Open-source model servers use simplified,
lowercase names (e.g.,
vllm
). Use GkeInferenceQuickstart.FetchModelServers to find available servers.
#model_server_version
def model_server_version() -> ::String
Returns
- (::String) — Optional. The model server version. Use GkeInferenceQuickstart.FetchModelServerVersions to find available versions. If not provided, the latest available version is used.
#model_server_version=
def model_server_version=(value) -> ::String
Parameter
- value (::String) — Optional. The model server version. Use GkeInferenceQuickstart.FetchModelServerVersions to find available versions. If not provided, the latest available version is used.
Returns
- (::String) — Optional. The model server version. Use GkeInferenceQuickstart.FetchModelServerVersions to find available versions. If not provided, the latest available version is used.