Class: Google::Cloud::GkeRecommender::V1::StorageConfig

Inherits:

Object

Object
Google::Cloud::GkeRecommender::V1::StorageConfig

show all

Extended by:: Protobuf::MessageExts::ClassMethods

Includes:: Protobuf::MessageExts

Defined in:: proto_docs/google/cloud/gkerecommender/v1/gkerecommender.rb

Overview

Storage configuration for a model deployment.

Instance Attribute Summary collapse

#model_bucket_uri ⇒ ::String
Optional.
#xla_cache_bucket_uri ⇒ ::String
Optional.

Instance Attribute Details

#model_bucket_uri ⇒ `::String`

Returns Optional. The Google Cloud Storage bucket URI to load the model from. This URI must point to the directory containing the model's config file (config.json) and model weights. A tuned GCSFuse setup can improve LLM Pod startup time by more than 7x. Expected format: gs://<bucket-name>/<path-to-model>.

Returns:

(::String) —
Optional. The Google Cloud Storage bucket URI to load the model from. This URI must point to the directory containing the model's config file (config.json) and model weights. A tuned GCSFuse setup can improve LLM Pod startup time by more than 7x. Expected format: gs://<bucket-name>/<path-to-model>.

# File 'proto_docs/google/cloud/gkerecommender/v1/gkerecommender.rb', line 551

class StorageConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#xla_cache_bucket_uri ⇒ `::String`

Returns Optional. The URI for the GCS bucket containing the XLA compilation cache. If using TPUs, the XLA cache will be written to the same path as model_bucket_uri. This can speed up vLLM model preparation for repeated deployments.