Class: Google::Cloud::GkeRecommender::V1::ModelServerInfo
- Inherits:
-
Object
- Object
- Google::Cloud::GkeRecommender::V1::ModelServerInfo
- Extended by:
- Protobuf::MessageExts::ClassMethods
- Includes:
- Protobuf::MessageExts
- Defined in:
- proto_docs/google/cloud/gkerecommender/v1/gkerecommender.rb
Overview
Model server information gives. Valid model server info combinations can be found using GkeInferenceQuickstart.FetchProfiles.
Instance Attribute Summary collapse
-
#model ⇒ ::String
Required.
-
#model_server ⇒ ::String
Required.
-
#model_server_version ⇒ ::String
Optional.
Instance Attribute Details
#model ⇒ ::String
Returns Required. The model. Open-source models follow the Huggingface Hub
owner/model_name format. Use
GkeInferenceQuickstart.FetchModels
to find available models.
401 402 403 404 |
# File 'proto_docs/google/cloud/gkerecommender/v1/gkerecommender.rb', line 401 class ModelServerInfo include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#model_server ⇒ ::String
Returns Required. The model server. Open-source model servers use simplified,
lowercase names (e.g., vllm). Use
GkeInferenceQuickstart.FetchModelServers
to find available servers.
401 402 403 404 |
# File 'proto_docs/google/cloud/gkerecommender/v1/gkerecommender.rb', line 401 class ModelServerInfo include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#model_server_version ⇒ ::String
Returns Optional. The model server version. Use GkeInferenceQuickstart.FetchModelServerVersions to find available versions. If not provided, the latest available version is used.
401 402 403 404 |
# File 'proto_docs/google/cloud/gkerecommender/v1/gkerecommender.rb', line 401 class ModelServerInfo include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |