Reference documentation and code samples for the Google Cloud Gke Recommender V1 Client class StorageConfig.
Storage configuration for a model deployment.
Generated from protobuf message google.cloud.gkerecommender.v1.StorageConfig
Namespace
Google \ Cloud \ GkeRecommender \ V1Methods
__construct
Constructor.
data
array
Optional. Data for populating the Message object.
↳ model_bucket_uri
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>
.
↳ xla_cache_bucket_uri
string
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.
getModelBucketUri
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>
.
string
setModelBucketUri
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>
.
var
string
$this
getXlaCacheBucketUri
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.
string
setXlaCacheBucketUri
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.
var
string
$this
