GKE Recommender v1 API - Class StorageConfig (1.0.0-beta01) 

public sealed class StorageConfig : IMessage<StorageConfig>, IEquatable<StorageConfig>, IDeepCloneable<StorageConfig>, IBufferMessage, IMessage

Reference documentation and code samples for the GKE Recommender v1 API class StorageConfig.

Storage configuration for a model deployment.

Inheritance

object > StorageConfig

Namespace

Google.Cloud.GkeRecommender.V1

Assembly

Google.Cloud.GkeRecommender.V1.dll

Constructors

StorageConfig()

public StorageConfig()

StorageConfig(StorageConfig)

public StorageConfig(StorageConfig other)
Parameter
Name Description
other StorageConfig

Properties

ModelBucketUri

public string ModelBucketUri { get; set; }

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>.

Property Value
Type Description
string

XlaCacheBucketUri

public string XlaCacheBucketUri { get; set; }

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.

Property Value
Type Description
string